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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation profile is known. The description adds a genuine cost disclosure ('action=safe is slow') beyond the annotations, which is useful. However, it doesn't disclose reversibility, what persists beyond the cache, or per-action side effects. No contradiction with annotations.

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 sentences with no waste: purpose and action list front-loaded, the action=help pointer in the middle, and the cost warning last. The 13-action enumeration is necessarily long but earned.

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 19-parameter, 13-action facade with no output schema, the description delegates per-action parameters and examples to action=help. This pattern is workable, but it leaves the agent without any routing guidance on which action fits which use case until it makes an initial help call, so the definition is not fully self-sufficient.

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 100% — all 19 parameters have descriptions in the schema, so the baseline is 3. The description adds no parameter-specific meaning, deferring to action=help for per-action parameter detail, which is acceptable given the schema already documents every field.

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 a specific resource (a codegraph-compatible safety and change-management facade) and enumerates all 13 dispatchable actions, which distinguishes it from the read-oriented siblings (search, nav, structure, viz). However, because it is a broad facade, the singular verb+resource is diluted across many capabilities, so it isn't as crisp as a single-purpose tool.

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 offers 'Pass action=help for per-action parameters and examples' as the only usage guidance, and the 'safety and change-management facade' framing implies it is the mutation path relative to read-oriented siblings. But there is no explicit when/when-not routing among its own 13 actions or against alternatives like search and structure.

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?

Annotations already indicate readOnlyHint and idempotentHint, so the description is not expected to repeat that. It adds useful behavioral context: the cost difference between actions (project slow vs file warm) and the ability to get help via action=help. This goes beyond annotations and helps set expectations for performance and discoverability.

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 concise: three sentences, each with a clear purpose. The first sentence states the tool's role and lists actions; the second gives a direct tip for help; the third provides a cost guideline. It is front-loaded with the core purpose and lists actions efficiently. Minor redundancy: actions are repeated in the schema description, but in the description it is necessary for clarity.

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 tool with 10 parameters and no output schema, the description does not fully cover usage details for all actions. It provides an escape hatch ('action=help') that compensates somewhat, and the cost guidance is helpful. However, given the complexity (16 actions), a more detailed explanation of what each action does or when to use it would be expected. The description is adequate but leaves the agent reliant on the help mechanism.

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 100%, so each parameter has a description in the schema. The tool description adds little beyond the schema; it mentions the 'action' parameter lists actions and suggests 'action=help' for per-action parameters, which is a useful pointer. The description's high-level mention of actions adds context but does not significantly deepen parameter understanding beyond the schema's descriptions.

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 that this is a 'code-intelligence health and analysis facade' and lists the available actions, which distinguishes it from sibling tools like 'edit' or 'index.' It explicitly mentions 'codegraph-compatible' to provide context. However, the purpose is somewhat generic ('health and analysis') and relies on the action list to convey specifics, lacking a single concise verb+resource statement.

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 implies usage by listing actions and suggesting 'action=help' for per-action details. It provides a cost hint ('project is slow, prefer file') which helps choose between actions. But it does not explicitly state when to use this tool versus alternatives like 'search' or 'structure,' nor does it mention when not to use it. The guidance is present but implicit.

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?

Annotations provide no useful safety profile (all hints are false/absent), so the description carries the full burden. It says 'lifecycle hub' but never discloses that build, cache, full, or sync may mutate or recreate indexes, nor what status or knowledge return. The help pointer is not a behavioral disclosure.

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, with two sentences and no obvious filler. The action list somewhat duplicates the schema enum and the help instruction is factually wrong, but structurally it is efficient.

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 multi-action, 11-parameter tool with no annotations and no output schema, this description is critically incomplete. It does not explain what any action does, which parameters apply to which action, what outputs to expect, or how this relates to sibling tools. The single promised expansion path, action=help, is invalid.

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 input schema already documents all parameters at 100% coverage, so the baseline is 3. However, the description adds the instruction 'Pass action=help', which contradicts the action enum and would cause a validation failure. It also provides no mapping of the 11 parameters to the eight actions.

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 tool as a code-intelligence index lifecycle hub and enumerates eight concrete actions, so an agent can infer the domain and operation set. It lacks a single verb+resource statement and does not explicitly distinguish itself from siblings like search, nav, or structure, but its scope is reasonably clear.

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 alternatives, and no prerequisites such as setting a project path. The only usage pointer is 'Pass action=help', which is not a valid value in the action enum and therefore cannot be followed as written.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the safety profile is covered. The description adds a performance warning for callers, which is useful beyond annotations. It does not disclose other behavioral details like rate limits, snapshot requirements, or how the 'context' warm cache behaves, but given the annotations, a 3 is fair.

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 (3 sentences) and front-loaded with the purpose, then the action list, then the crucial performance tip. No wasted words, though the action list is long and could be considered noisy; but it is necessary. The structure is efficient.

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 13 parameters with no output schema and 16 possible actions, the description is not sufficient for an agent to call this tool correctly without additional help. It offloads detail to action=help, which may be acceptable but is not self-contained. The tool is highly polymorphic and requires per-action documentation; the description should at least summarize common action groups or link each action to its parameters. The performance note helps but is not enough.

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 100%, so the schema fully documents all 13 parameters. The description adds minimal extra meaning beyond listing actions; it does not explain how parameters combine per action (e.g., which subset applies to which action). The instruction to use action=help partially compensates but isn't inline here.

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 tool as a code-intelligence navigation facade and lists its 16 actions explicitly, which disambiguates the purpose despite the terse verb 'nav'. It does not define what each action does beyond their names, but the list itself provides enough orientation for an agent familiar with code-intelligence terminology.

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 one concrete usage hint: for callers, prefer 'context' (1-hop, warm) because callers is slow. It also instructs to pass action=help for per-action parameters. However, it does not explain when to use the tool vs siblings like search or structure, nor does it provide general selection criteria between the many actions.

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?

Annotations are all false, so the description carries the burden of behavioral disclosure. It does not state whether actions are read-only, whether they mutate project state, whether they require a project path to be set, or what side effects (e.g., doc_sync) may occur. The description adds no behavioral context beyond the action names.

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-loads the tool's role, then lists actions and points to help. It is efficient, though the action list is somewhat long and could be trimmed since the schema already enumerates the enum values.

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 multi-action hub with 10 parameters and no output schema, yet the description does not explain what each action returns, how actions relate, or what prerequisites exist (e.g., set_project_path sibling). The pointer to action=help shifts the burden to runtime help, which is not available to the agent at selection time. The description is incomplete for correct tool selection and 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 100%, so the schema already documents all parameters. The description adds no parameter-level meaning beyond the schema, but the baseline of 3 applies because the schema does the heavy lifting. The description's mention of action=help is a minor addition.

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 tool as a 'project-intelligence hub' with a list of actions, which conveys a general purpose but not a specific verb+resource. It distinguishes itself from siblings only by naming its sub-actions; it doesn't state what the hub actually does (e.g., analyze, manage, or retrieve project intelligence). The action list provides some clarity but the overall purpose remains vague.

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 says to pass action=help for per-action parameters and examples, which is a useful usage pointer. However, it does not explain when to use this tool versus siblings like search, structure, or viz, nor does it describe which action to choose for which scenario. The guidance is implied rather than explicit.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds some behavioral context by noting it is a codegraph-compatible facade and that each action has its own parameters/examples via action=help, but it does not say what the tool returns or how actions behave beyond requiring an action discriminator.

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: two sentences that front-load the tool's purpose, enumerate the action surface, and point to the help mechanism. No filler or redundant explanation.

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 complex facade with 9 distinct actions and 11 parameters, but the description gives no per-action semantics, no guidance on choosing an action, and no indication of return behavior. The action=help escape hatch is helpful but shifts most of the burden onto the agent to make additional calls before it can invoke the tool correctly.

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 100%, so the schema already documents all 11 parameters. The description does not add significant parameter meaning beyond pointing to action=help for per-action details, which is useful but not required since the action enum is already in the 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?

The description states a specific resource ('Code-intelligence search facade') and lists the exact actions it dispatches to, so an agent can tell it is a search-oriented tool. It is less clear on what the facade does as a whole or how it differs from sibling tools like nav, structure, and viz, but the scope is reasonably identifiable.

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 guidance on when to use this tool versus alternatives, nor any exclusion criteria. The only usage hint is 'Pass action=help for per-action parameters and examples', which explains how to get more details rather than when this tool should be selected.

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; description adds context about security boundaries and being the first step, but does not detail side effects, idempotency, or error handling.

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 concise sentences front-loading purpose and usage. No unnecessary 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?

Adequate for a simple setter tool: explains why it's needed (security, file resolution) and gives usage instruction. Lacks return value info but acceptable.

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 100% with 'Absolute path to the project root'. Description repeats this without adding new constraints, format, or examples.

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?

Description clearly states 'Set the project root path for security boundaries' and identifies it as the first step, distinguishing it from sibling tools which are likely not initialization tools.

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 says 'Call this before any other tool', providing clear when-to-use guidance, but lacks when-not-to-use or alternative tool mentions.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context by calling it a facade and noting that action=help reveals per-action details, but it does not disclose behavior like result shape, error cases, or whether certain parameters are ignored per action.

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 sentences and front-loads the core purpose before listing actions and the help mechanism. Every sentence earns its place; there is no filler or redundant restating beyond the action list, which is useful for orientation.

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 multi-action facade with 11 parameters and no output schema, the description gives a reasonable starting point and tells the agent how to get more detail via action=help. Still, it lacks per-action eligibility guidance, expected outputs, or any mapping of use cases to actions, so it 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?

Since schema description coverage is 100%, the schema carries most parameter meaningainer and baseline is 3. The description adds only the action=help hint rather than deeper per-action parameter semantics; it does not compensate for vague schema descriptions like 'Action sub-mode' or 'Action discriminator.'

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 labels this as 'code-intelligence (codegraph-compatible) structural analysis facade' and enumerates the nine actions, which tells an agent what domain and capabilities the tool covers. It is not a tautology and is distinct enough from siblings like search/nav/edit/viz, though it does not explicitly name those alternatives.

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 a clear general context (structural analysis) and the practical instruction 'Pass action=help for per-action parameters and examples,' which helps an agent begin. However, it does not explain when to use this tool instead of a specific sibling, nor does it provide an exclusion or best-fit action selection.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it is codegraph-compatible and that action=help exposes per-action behavior, but it does not disclose what each action returns or any action-specific side effects.

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 sentences with no filler. The core purpose is front-loaded, the action list is compact, and the help instruction is placed last as a natural follow-up. Every sentence 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 description is adequate as a starting point but relies on a separate action=help invocation to fill in per-action semantics, required parameters, and examples. Given 14 parameters and no output schema, an agent cannot confidently select and invoke the right action from the description alone.

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 100%, so the schema already documents all 14 parameters. The description adds no parameter details beyond pointing to action=help for per-action parameters and examples, which does not exceed the baseline expected when the schema is fully self-describing.

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 identifies a code-intelligence visualization and similarity facade and enumerates the four actions (graph, knowledge, similarity, uml). This distinguishes it from sibling tools like search, nav, or structure at a high level, though 'facade' leaves the exact per-action purpose vague.

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 phrase 'visualization and similarity facade' implies when to use this tool, and 'Pass action=help' tells the agent how to discover usage details. However, there is no explicit comparison to sibling tools such as search or structure, and no stated when-not-to-use conditions.

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