Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden but discloses little beyond the happy path: it does not say whether the call fails on an unknown block_type, whether a graph must already exist, whether the block is auto-connected, or what side effects occur in the live session. Only the name-derivation default is disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One scope sentence followed by three labeled parameter notes, each carrying non-obvious information. Nothing is repeated from the schema and nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The existence of an output schema removes the need to describe return values, and the parameter notes are thorough. However, for a mutation on graph state with zero annotation coverage, error behavior and graph prerequisites are missing pieces an agent would want.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, yet all three parameters are explained with concrete formats and examples: block_type's exact catalog-id syntax, name's derived default (signal_generator0-style), and the important rule that parameters should contain only values differing from defaults. This is exactly the compensation a bare schema needs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ("Add a block instance to the current graph") that is clearly distinct from siblings like new_graph, remove_block, and connect. It does not explicitly say how it differs from set_parameters or update_block_settings, but the action itself is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage context by anchoring to "the current graph" and requiring an exact catalog id, which suggests search_blocks/describe_block should come first, but it never states prerequisites or when to prefer this over alternatives like load_graph. Usage is inferable rather than instructed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so: it discloses that attaching stops the managed backend and loses its sessions, that gr4-mcp never stops an attached backend, that sessions are shared with other clients, and that the URL is not persisted because ports change per launch. These are exactly the side effects and lifecycle constraints an agent needs before calling a switching tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence front-loads both directions of the operation and the rest is dense with non-redundant detail. Minor deduction for awkward line-wrapped formatting that splits the url explanation across lines, making it slightly harder to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter backend-switching tool with an output schema, the agent gets everything needed to choose a target and understand consequences. Missing only failure-mode guidance (invalid URL, 'studio' not found, unreachable host), which would matter for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does: it specifies the URL format (http:// optional), the literal sentinel value 'studio' with its lookup location (GR4 install var/logs), and the meaning of omission (return to gr4-mcp managed backend, which is the default). This fully documents the single parameter beyond the bare anyOf string schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Attach to an already running gr4cp_server') plus the inverse operation ('or go back to a private one'), so an agent can distinguish it from backend_status or list_sessions without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives the three concrete modes of the url argument (explicit URL, 'studio' lookup, omit for the managed backend) and contextualizes when each applies (gr4-studio launched it). It lacks explicit exclusions, such as what to do if the URL is unreachable or which sibling to call first to discover a running backend.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description must carry behavioral disclosure. 'Show' implies a read-only diagnostic, and the explicit note that a missing install is reported rather than erroring is a meaningful behavioral trait with remediation. However, there is no explicit statement that the tool performs no mutation, nor any handling of the case where the managed backend is not running (which the sibling attach_backend suggests is possible).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences: the first front-loads the full inventory of reported items, the second handles the empty-install edge case with a pointer to the fix. Every clause earns its place and nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters and an output schema present, the description needn't explain return values, and it still summarizes them well plus the missing-install failure mode. The remaining gap is that a managed backend may not be attached (per the attach_backend sibling) and the description does not say what happens then or which tool to call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so per the baseline this scores 4. No parameter semantics are needed or expected, and the description correctly spends no space on arguments.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Show') and enumerates exactly what is reported: the GNU Radio 4 install in use, the managed gr4cp_server backend with URL/pid/log, catalog size and schedulers. This is far more concrete than the bare name, but it never explicitly contrasts itself with adjacent status/listing siblings such as session_status or list_sessions, leaving the agent to infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives one concrete conditional path: when no GR4 install is found, the result says so and the agent should call set_gr4_install. That is a genuinely useful when-not/alternative pairing, but it covers only a failure branch — there is no statement of when to call this rather than session_status, list_sessions, or attach_backend in the normal case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It discloses useful mechanics (single-port omission, dynamic base-name resolution, explicit 'in#1' handles, exact type matching), but omits side effects (graph mutation), error/failure behavior beyond type mismatch, and idempotency. Partial disclosure for a no-annotation mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the primary action, then layers port rules efficiently. Three sentences, each earning its place, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values needn't be explained, and the port semantics are well covered for a tool with dynamic ports. Gaps remain around mutation side effects and error conditions, which matter given zero annotation coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains source_port/target_port behavior thoroughly (omission, dynamic base name vs. explicit handle), but leaves the meaning of source/target ambiguous (block ID vs. name) and never clarifies their string format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb and resource: 'Connect source block's output port to target block's input port.' This clearly distinguishes it from siblings like disconnect, add_block, and set_parameters without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides operational context for port omission and dynamic port naming, but gives no guidance on when to use connect versus alternatives like add_block or set_parameters, nor when it would fail or when to prefer another approach. Usage is implied rather than routed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden — and it discloses almost nothing beyond the verbs themselves. It does not say whether delete is irreversible, what happens to a running session's state or streams on stop, whether restart preserves configuration, what permissions or backend attachment are required, or what happens if the target session is already stopped or does not exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the operation set and appends the scoping default in parentheses. Nothing is wasted and the parenthetical default is placed exactly where it is needed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and the two-parameter surface is small. But for a destructive mutation tool with zero annotation coverage, the definition should say more about consequences (delete semantics, state loss on stop) and prerequisites than a single clause provides.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate: it does so for session_id by stating the default is the current graph's session, which is genuinely useful context not present in the schema. The action parameter is self-describing via its enum, but neither parameter is explained beyond that — no id format, no note on whether session_id is honoured for 'start'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names concrete verbs (start, stop, restart, delete) acting on a specific resource (a session), and the scope default ("the current graph's session") is stated. It is clear what the tool does, but it does not distinguish itself from the related siblings list_sessions or session_status, which an agent might reasonably confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the tool is clearly the mutation counterpart to the read-only session siblings, but neither the description nor anything else explicitly says when to use this versus list_sessions/session_status. The note that the default target is the current graph's session is the one piece of real targeting guidance; there are no preconditions (e.g. session must exist to stop/restart) and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description does real work: it discloses the default start behavior, that replace_previous stops AND deletes the previously deployed session (a destructive side effect), and that a failed start deletes the new session and surfaces the runtime error. Missing only auth/permission requirements and whether the call is idempotent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the primary behavior and followed by the two conditional/side-effect clauses. No filler, no repetition of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-boolean-parameter deployment tool with an output schema, the description covers defaults, the destructive replace behavior, and failure cleanup. Only preconditions (auth, graph validity requirements) are left unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it largely does: replace_previous is explained in terms of exactly what it stops and deletes, and 'by default' conveys start=true. It does not explicitly describe start=false (create without starting), leaving that one inference to the reader.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names specific operations (validate, create a backend session, start it) on a specific resource (the graph), which clearly separates it from siblings like validate_graph, save_graph or control_session. The multi-step nature is stated up front, though it does not explicitly say how it differs from chaining validate_graph + new session.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the operation sequence: this is the 'make it live' step, and replace_previous=default-true signals redeploy semantics. However, no alternative is named — nothing says to use validate_graph for a dry run, control_session to start/stop an existing session, or how to choose replace_previous=false.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses useful behavioral detail that advanced parameters are hidden unless include_advanced is set, and it implies a read-only descriptive operation, but it does not state permissions, read-only status explicitly, or how block type names should be obtained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two tightly focused sentences with zero filler. The main output scope is front-loaded, followed immediately by the include_advanced behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, has an output schema, and the description explains what kind of information is returned plus the include_advanced conditional behavior. It could be more complete by indicating where valid block_type values come from, but the essential call context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does so reasonably well: 'one block type' clarifies block_type, and the second sentence explicitly explains the effect of include_advanced on the returned content.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb and resource: it describes ports, parameters, and type variants of one block type. It is distinct enough from generic graph tools, but it does not explicitly differentiate itself from siblings such as get_block_settings or search_blocks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives like get_block_settings or search_blocks. The only usage-adjacent detail is the include_advanced flag behavior, which is parameter guidance rather than tool-selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, so description carries the burden. It clearly states the destructive action (remove) and the optional port scoping (default removes all connections between source and target; with ports, only those). However, it omits critical behavioral details: error handling if no connection exists, reversibility, permissions, and whether the operation is atomic.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence that conveys the action and optional scoping without waste. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive graph mutation tool with no annotations and 0% schema coverage, the description is too sparse. Output schema covers return values, but the description should specify what source/target refer to and error behavior. It provides only the bare minimum.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage. The description partially clarifies the optional port parameters ('optionally only between the given ports'), explaining that they restrict the removal. But it does not explain the core source and target parameters—whether they are block names, IDs, or something else—leaving the required parameters ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (remove) and resource (connections) with scope (source to target), but does not explicitly differentiate from the sibling connect tool, which is the likely inverse. An agent can tell it's about removal, but sibling routing isn't addressed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no alternatives, no prerequisites. The description only states the action; it doesn't say when to choose disconnect over connect or other tools, nor does it mention what happens if there are no connections.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the burden: 'Read' implies non-mutating and 'in a running session' hints at a runtime precondition, which is useful. It does not disclose failure behavior when the session is absent or stopped, nor how the default session is resolved, nor confirm the read-only profile explicitly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the runtime scoping qualifier comes right after the core action. Nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the core action plus targeting are clear. The gaps are the unaddressed session_id semantics and the lack of any stated runtime precondition, which matter for a live-session read tool with no annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It helpfully clarifies that `block` is an instance name rather than a block type or ID, but `session_id` is never mentioned, so the meaning of defaulting to null (current/default session vs auto-resolve) is left undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('read the live settings of a block') plus scope ('in a running session'), which implicitly separates it from update_block_settings and from static metadata tools. It never names a sibling, so an agent must infer the contrast with describe_block or list_categories.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'In a running session' implies the live-state context, but there is no explicit when-to-use versus describe_block (static info) or session_status, and no stated prerequisites such as needing an attached/active session. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral burden, and it does disclose that categories are returned along with block-type counts. It does not state that this is a side-effect-free read or say anything about ordering/size of the returned list, but for a zero-parameter listing tool the risk surface is small.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the verb and resource, with parenthetical examples and the return payload stated compactly. Nothing wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return structure need not be explained, and with zero parameters and no annotations there is little else to cover. The only missing piece is ordering/determinism of the returned list.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The category examples are illustrative of output, not inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (List) and resource (block categories) and grounds it with concrete examples (blocks/math, blocks/filter, studio) plus what comes back (block-type counts). An agent can distinguish it from siblings like search_blocks or get_block_settings, though the description never explicitly contrasts them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites, and no pointer to alternatives such as search_blocks for finding individual blocks. The only signal is implied by the verb 'List'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It implies a read-only listing and names returned fields, but it does not state whether a backend must be attached, whether results are paginated or ordered, or what permissions are needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence that clearly states the action, scope, and returned fields with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a no-parameter listing tool with an output schema, the description is sufficient to call it correctly. It could be slightly stronger by mentioning backend connection prerequisites, but no critical context is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameter semantics and correctly introduces no extra parameter behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb and resource ('List all sessions on the backend') and lists the returned fields, so the agent knows exactly what the tool does. It does not explicitly contrast itself with the sibling session_status, but 'all sessions' provides some distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus session_status, control_session, or backend_status. The description implies a listing use case but offers no exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose a genuinely important behavior: unknown blocks, unsupported expressions and invalid connections are 'skipped and reported' rather than causing failure. It stops short of saying what happens to the previously loaded graph or what error surfaces if the path is bad.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core action and file formats, followed by the fallback behavior. Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the skip-and-report behavior is covered. However, for a state-changing load with no annotations, the description omits whether the current graph is discarded, whether unsaved edits are at risk, and what happens on an unreadable or missing file.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single `path` parameter has 0% schema description coverage, so the description must compensate — and it does, by naming the file extensions accepted for that path (Studio .gr4s vs GRC YAML .gr4c/.grc/.yaml). It does not clarify absolute vs relative paths or quoting requirements.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Load') and resource ('a .gr4s / .gr4c / .grc / .yaml file as the current graph'), and enumerates the accepted formats, which plainly separates it from new_graph, save_graph and show_graph. It does not name a sibling explicitly, but the operation is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the phrase 'as the current graph' suggests this replaces the active graph, but the description never says when to choose it over new_graph or how it relates to save_graph/deploy_graph. No preconditions (file must exist, path format, whether unsaved work is lost) are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full behavioral burden, and it does disclose the key destructive trait: the current unsaved graph is replaced. It does not say whether there is a confirmation prompt, whether saved graphs on disk are unaffected, or whether the returned object identity matters — real gaps for a no-annotation mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the scope and the destructive side effect appear immediately. Nothing in the sentence could be removed without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema exists, so return values need not be explained, and the core novelty plus destructive behavior are covered. What remains missing is parameter guidance in the absence of any schema descriptions, which leaves the tool slightly under-specified for a mutation call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters, so the description must compensate and it says nothing about 'name' or 'description'. An agent cannot infer from the text whether the name defaults to 'untitled', whether an empty description is acceptable, or whether either affects the created graph's identity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: creates a new, empty flowgraph. The parenthetical adds the crucial scope that it is empty and replaces the unsaved current graph, which distinguishes it from load_graph in intent. It stops short of explicitly naming the sibling it differs from, so it lands at 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: call it when you want a blank graph rather than an existing one, and the note about replacing the unsaved graph hints this is a starting point. However, it never states when to prefer load_graph or save_graph first, nor whether unsaved work should be saved beforehand — that routing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden and mostly succeeds: it explains that output is summarized by default, lists summary statistics, describes dominant period and peak behavior, notes that raw returns a full single-stream payload that can be very large, and caps downsampled points via max_points. It does not explicitly state read-only safety or error behavior, but the behavioral detail is strong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the tool's purpose, then efficiently details stream selection, default summarization, and raw behavior. It is dense but not bloated; each sentence adds useful operational context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is largely complete for understanding output summarization versus raw payloads, and an output schema exists so return values need not be explained. However, it omits session_id semantics and does not clarify how to target a specific running session beyond the phrase 'running session'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry all parameter meaning. It documents stream as a sink block name defaulting to every stream, explains raw=True returns a single stream's full payload, and mentions max_points in the downsampling behavior. However, session_id is never described, leaving one of four parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb and resource: read the latest data from Studio sink blocks (scope, spectrum, scalar, waterfall, XY) of a running session. It distinguishes this data-reading operation from sibling tools like get_block_settings and list_sessions by focusing on sink output streams.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage guidance is implied through parameter behavior: default is all streams summarized, raw=True returns a single stream's full payload. However, it does not explicitly say when to choose this tool over siblings such as get_block_settings or session_status, nor does it state prerequisites beyond 'running session'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the most important behavioral trait: deletion cascades to all touching connections. It omits irreversibility, permission requirements, and what happens if the block does not exist or is a required endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the action and immediately followed by the consequence. No filler and nothing that could be trimmed without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, and with a single parameter and simple structure the description covers the essential destructive semantics. The main residual gap is identifying the block correctly by 'name', which is left entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the single 'name' parameter, and it says nothing about it — not whether it is a block name vs. an ID, its uniqueness scope, or its format. The one substantive detail (cascade) is about effects, not the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear specific verb + resource ('Remove a block') with an added scope qualifier ('and every connection touching it') that distinguishes it from the sibling 'disconnect', which removes a single connection. It stops short of explicitly naming that alternative, so it's clear rather than fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of when to prefer 'disconnect' (targeted edge removal) over this cascading removal. An agent must infer the choice from the sibling name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It usefully discloses that the extension chooses the format and that .gr4c is inline GRC YAML exactly as submitted to the backend. However, it does not state whether saving overwrites an existing file, whether parent directories are created, or what permissions or side effects apply to this write operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and front-loaded with the core action. The format list is compact and each detail directly helps the agent choose between .gr4s and .gr4c, with no wasted sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter save tool with an output schema, the description covers the essential call behavior: save the graph and use the extension to select the format. The main remaining gap is overwrite and filesystem side-effect behavior, which is relevant for a write operation but less critical given the low complexity and existing output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does add meaningful semantics by explaining that the file extension determines the output format, which directly informs how the required path parameter should be chosen. It still does not describe the path parameter itself, such as whether it must be a full file path or whether directories must already exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Save the graph.' It also explains that the file extension controls the output format, distinguishing .gr4s from .gr4c. It does not explicitly differentiate this tool from siblings like load_graph, deploy_graph, or show_graph, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the action 'Save the graph' and by the format guidance for .gr4s and .gr4c, but there is no explicit when-to-use guidance or comparison to sibling tools such as deploy_graph or validate_graph. An agent can infer that this writes a graph to a path, but alternatives are not addressed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does substantial work: it discloses AND semantics ('every word must match'), the ranking model (whole words in name, then first sentence of summary), synonym expansion ('noise' finds AWGN), and the grouped-per-family return shape. The main omission is how `limit` affects result truncation or paging, which matters for a search endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded, followed by matching rules, then the grouping/output contract, then per-parameter notes. Every sentence conveys useful information, though the description is dense and slightly long; it remains reasonably structured rather than bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with an output schema already present, the description covers enough: matching semantics, ranking, grouping, and filter usage. Since return values are documented by the output schema, the only real gap is the unexplained `limit` behavior (pagination/truncation).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does so well for three of four parameters: `query` (words matched against name/category/summary), `category` (prefix filter with example values), and `port_type` (filter with example types). `limit` is never mentioned in the description, leaving one parameter to be inferred from its name and default alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search the block catalog by words in the block name, category or summary') and immediately describes ranking. It also names the downstream siblings (describe_block / add_block) and the exact strings they consume, so an agent can distinguish this lookup tool from the mutation/graph tools in the sibling list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the intended workflow clearly: search here, then feed a concrete block_type string to describe_block or add_block. It also documents when to use the `category` prefix filter and `port_type` filter. There are no explicit exclusions or comparison against list_categories, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It delivers one genuinely valuable caveat — that a graph whose blocks all finished still reports "running" — which prevents a real misinterpretation, but it omits whether this is a side-effect-free read, what errors occur for an unknown session_id, or anything about auth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, default behavior front-loaded, zero filler. 'incl. stream endpoints' is slightly compressed and reads as a dangling fragment, which keeps it just short of ideal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value detail is not needed, and the default-plus-status-quirk note covers the main behavioral risk. What's still missing for a status tool among many session-related siblings is any disambiguation from list_sessions and control_session.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% for the single session_id parameter, whose schema entry is a bare nullable string with default null. The description partially compensates by explaining what the default resolves to (the session deployed from the current graph), but it gives no format or acceptance details for an explicit id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the resource (session) and what it returns (state, including stream endpoints), with a scope note about the default session. It is clear on its own, but it never names or contrasts with the obvious alternatives in the sibling list (list_sessions, control_session, backend_status), so an agent must infer the boundary itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The parenthetical 'default: the one deployed from the current graph' tells you what happens when you omit session_id, which is a genuine usage cue. However, there is no explicit statement of when to pick this over list_sessions (enumerate sessions) or control_session (act on a session), so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so well: it warns that the backend is restarted, running sessions are lost, the block catalog is reloaded, persist saves the setting to config, and GR4_PREFIX still takes precedence.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it states the core action first, then acceptable path forms, side effects, and persistence behavior. Every sentence adds relevant operational detail without waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the important operational facts an agent needs before calling this side-effecting tool: accepted path forms, restart/session-loss implications, catalog reload, persistence, and environment-variable precedence. An output schema exists, so return-value details are appropriately not repeated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains that path may be the install prefix, its bin/ folder, or the gr4cp_server binary, and it explains that persist=True saves the choice to the gr4-mcp config file; it does not explicitly describe persist=False behavior beyond implication.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: register a GNU Radio 4 install for the backend to run from, with a concrete example path. It is clear what the tool does, but it does not explicitly differentiate itself from related siblings such as attach_backend or backend_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when this tool is relevant: setting the GNU Radio 4 install that the backend should run from. It does not explicitly state when to prefer alternatives or when not to use it, so it falls short of full alternative-routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and delivers well: it discloses that values are validated against the catalog, that null resets to the block default, and that the change is graph-only rather than live-session. It stops short of stating permissions, failure behavior when validation fails, or whether changes are reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the primary action and followed by the two facts an agent actually needs (null reset, graph-vs-session routing). Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, an output schema available, and a nested-object parameter, the description covers the critical semantics — validation, reset behavior, and graph-only scope. The remaining gap is the meaning of `name` and the shape of `parameters`, which no structured field documents.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate and does partially: it explains null-value reset semantics and catalog validation for the nested `parameters` object. It never clarifies that `name` identifies the target block (by id or name) or what keys the parameters object accepts, leaving meaningful gaps for a 0%-coverage schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — setting parameters on a block in the graph — and qualifies the scope with 'validated against the catalog' and 'edits the graph only'. The sibling update_block_settings is named and differentiated, so an agent can distinguish it without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: 'This edits the graph only; use update_block_settings to change a running session.' That names the alternative and the condition that selects it, leaving no ambiguity about graph-state vs. session-state edits.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden of behavioral disclosure. It makes the returned contents clear and explains the include_grc option, but it does not explicitly confirm read-only behavior, side effects, or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two tight sentences, front-loads the primary output, and uses the second sentence only to explain the sole optional parameter. There is no redundant restatement of the tool name or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one optional parameter and an output schema, the description is largely complete: it states what is returned and clarifies the only parameter. The main remaining gap is the lack of explicit positioning among sibling graph tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description compensates by explaining that include_grc adds the GRC YAML that deploy_graph would submit. This gives the boolean parameter meaningful context beyond its type and default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource precisely: the current flowgraph, including blocks, set parameters, ports, and connections. It also clarifies the optional GRC YAML output. It stops short of explicitly distinguishing this from sibling inspection tools such as get_block_settings or validate_graph.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: call this to inspect the current graph, and set include_grc when the YAML that deploy_graph would submit is needed. There is no explicit when-to-use/when-not guidance or comparison to sibling graph-inspection tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses catalog validation and that values are written into the graph for later save/deploy, but it omits critical behavior around staged vs immediate mode, session prerequisites, and failure or permission behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two tight sentences with the primary action front-loaded and a useful conditional side-effect note second. The inline JSON example is efficient and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a mutation-like tool with no annotations, 0% schema description coverage, and an important mode enum that is not described. The output schema reduces the need to explain return values, but the description remains incomplete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for four parameters, so the description must compensate and largely does not. It gives an example for settings and hints at session context, but does not explain the mode enum values, session_id selection, or how block is identified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: changing block settings in a running session, with a concrete settings example. It does not distinguish this tool from similar siblings such as set_parameters or get_block_settings, so the purpose is clear but not fully disambiguated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'in a running session' and the current-graph condition, but the description never explicitly says when to use this tool instead of set_parameters or get_block_settings. There are no stated exclusions or prerequisites beyond the vague current-graph note.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description has to carry the full burden; 'Check ... locally' does imply a non-destructive, client-side operation that doesn't touch the backend, which is useful. However it never explicitly states it is read-only, whether it mutates the graph, or whether failures block subsequent operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence listing the four check categories with zero padding. The fragmentary style is terse but every element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema covers return values and there are no parameters, so the remaining gaps are small but real: whether a graph must be loaded/open first, and what the agent should do with a failed validation. For a simple validator this is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate. The description does not misuse the space with parameter talk.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (validate the graph) and enumerates exactly what is checked: missing blocks, port counts, unconnected blocks, no sink. That level of specificity distinguishes it from siblings like show_graph or save_graph, though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The word 'locally' implies this is a pre-deploy/pre-save check rather than a backend operation, but no when-to-use or when-not-to-use guidance is given and no alternative (e.g. deploy_graph) is named. Usage must be inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.