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 usefully discloses that the created diagram is empty and that the response is the new diagram's id, but says nothing about permissions/auth requirements, error conditions, or naming-collision 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?

Three short sentences, front-loaded with the core action and return value, followed by the two follow-up hints. Every sentence earns 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?

For a simple three-parameter creation tool with no annotations and no output schema, the description covers the action, the optional folder, the returned id, and the next-step tool. Only permission/prerequisite context is absent, which is a minor gap at this complexity level.

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 all three parameters are already documented in the schema, including the folder_id lookup hint and title examples. The description only restates that folder placement is optional and where to get folder_id, adding no new syntax or constraint detail. Baseline 3 is appropriate.

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 (create a new empty diagram) with scope (in a workspace, optionally in a folder) and explicitly separates itself from generate_diagram, which populates content. An agent can distinguish it from create_folder, update_diagram, and generate_diagram without opening any 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?

Gives explicit sequencing and alternatives: call generate_diagram afterward to populate, and list_folders first to obtain a folder_id. It lacks any when-not-to-use guidance (e.g. 'do not use to import existing diagrams'), so it stops just short of the top score.

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 usefully discloses that the tool returns the new folder's id and name and that nesting is optional, but it omits permissions, side effects, error behavior, and uniqueness constraints. Some value is added, but major gaps remain.

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 core action, followed by return value and optional behavior. Every sentence earns its place with zero 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?

For a low-complexity create tool with no output schema, the description covers the essentials: what is created, where, the return values, and the optional nesting. Missing details like permission requirements are minor given the tool's simplicity and the full schema 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 100%, so the schema already documents all three parameters. The description reinforces the optional parent-folder nesting ('Optionally nest it inside an existing folder'), but adds no syntax, format, or constraints beyond what the schema provides. Baseline 3 is appropriate.

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 ('Create a new folder in a workspace') with a clear scoping phrase. The resource 'folder' distinguishes it from sibling tools like create_workspace and create_diagram without requiring explicit sibling references.

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 when-to-use guidance, no conditions, and no alternatives named (e.g., list_folders or create_workspace). The purpose implies usage, but the description offers no help in selecting this tool over others or knowing prerequisites.

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 discloses the return values ('id and name'), but omits key mutation traits such as required permissions, duplicate-name handling, idempotency, or 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 short, front-loaded sentences with no wasted words. Purpose is stated first, followed by return 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?

For a simple one-parameter creation tool, the description covers purpose and return values. However, it lacks usage guidance and behavioral context (e.g., permissions, uniqueness constraints), which matters because there are no annotations and no 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 100%, so the schema already documents the single parameter. The description adds no further parameter semantics, making the baseline score of 3 appropriate.

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 ('Create a new workspace'), which clearly distinguishes it from list_workspaces. However, it does not explicitly differentiate itself from other creation siblings like create_folder or create_diagram.

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 no guidance on when to use this tool versus alternatives, prerequisites, or exclusions. The purpose implies usage, but no explicit context is given.

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 discharges the most important part: the operation is permanent, irreversibly destroys the diagram and its content. It omits secondary traits such as required permissions, behavior when the diagram_id does not exist, or whether deletion cascades to shares/links.

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, zero waste, with the destructive consequence front-loaded in the first sentence and the irreversibility warning second. Nothing could be trimmed without losing signal.

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 single-required-parameter destructive tool with no output schema, the definition covers the essentials an agent must know before calling it. It falls just short of complete by not addressing failure modes (unknown or already-deleted diagram_id) or authorization requirements.

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% for the single parameter ('The diagram UUID to delete'), so the schema already carries the semantics. The description adds nothing for the parameter beyond the baseline; per the rubric this is the standard 3 when the schema does the heavy lifting.

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 (delete) and resource (diagram) plus the scope of destruction ('and its content'). It is immediately distinguishable from siblings like update_diagram, create_diagram, or get_diagram_scene without opening any 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?

No when-to-use, when-not-to-use, or alternative is named. It never says to prefer update_diagram when content should be cleared without removing the diagram, nor does it state prerequisites such as ownership or permissions. Usage is only inferable from the tool name.

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 well: it discloses that layout is automatic (do NOT compute x/y), that 'replace' clears existing content while 'append' preserves it (a destructive-behavior disclosure), and that the target must already exist. It stops short of describing failure modes or what the call returns.

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-loaded with the core purpose, then cleanly sectioned into NODES / EDGES / MODE blocks that map to the parameters. It is somewhat long, and lines like 'Every important relationship should be an edge' echo the preceding sentence, but no section 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?

For a mutation tool with no annotations and no output schema, the description supplies the crucial missing behavioral context (auto-layout, destructive replace semantics, prerequisite that the diagram exists). It does not say what happens on invalid node/edge references or what the agent gets back on success.

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 already 100%, so baseline would be 3, but the description adds genuine semantic guidance beyond the schema: how many nodes/edges to create and on what basis (one per distinct component, one per data flow/API call/dependency), plus edge-labeling intent. It largely restates the mode and diagram_id meaning already given 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 opening sentence names a specific verb (generate) and resource (visual diagram) and states the source (structured graph of nodes/edges) and destination (existing CanvasKeep diagram). It clearly distinguishes itself from create_diagram by requiring an existing diagram_id and pointing to create_diagram for setup.

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 concrete usage instructions: supply logical structure only, let CanvasKeep handle layout, one node per component, one edge per meaningful interaction, and explains replace vs append. It references create_diagram as a prerequisite for obtaining the diagram_id, but never states when NOT to use this tool versus siblings like save_diagram_scene or update_diagram.

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 disclose meaningful behavior: embedded image data is omitted by default because it can be very large, and elements include arrow bindings and appState. It does not mention permissions or error behavior, but the payload-shaping behavior is well communicated.

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 tight paragraphs: purpose first, then the workflow pairing, then the one caveat about files. No filler sentences and the most important routing information is front-loaded.

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?

There is no output schema, so the description must describe the return shape, and it does: the full elements array and appState, with the notable omission of file blobs by default. Nothing an agent needs to call this correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real value by explaining why include_files defaults to false (embedded base64 data can be very large) and by detailing what the returned elements contain. This goes beyond restating 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 names a specific verb and resource ('Read the raw Excalidraw scene of a diagram') and enumerates exactly what is returned (elements array with ids, x/y, width/height, styles, text, arrow bindings, plus appState). This clearly separates it from siblings like get_diagram_summary or list_diagrams.

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 states the exact workflow: use this before save_diagram_scene, modify the elements, then write the complete array back. That names the alternative and the condition that selects it, so an agent knows precisely when to pick this tool over its siblings.

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 disclosure burden. It does useful work by defining the payload boundary (metadata only, no scene data), which signals a cheap read operation, but it says nothing about permissions, behavior when the diagram_id does not exist, or error semantics. Adequate but incomplete for a zero-annotation 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?

Two sentences, zero filler, with the returned-field list front-loaded and the exclusion clause placed last where it is most useful. Every clause 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?

With no output schema and no annotations, the description compensates well by enumerating the returned fields and their boundary. It is nearly complete for a simple read-only lookup, though it omits not-found/permission behavior an agent might want before calling.

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?

There is a single parameter, diagram_id, and schema description coverage is 100% ('The diagram UUID to look up'), so the schema already does the heavy lifting. The description adds no format or lookup semantics beyond that, making the baseline 3 correct.

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 ('Get a summary of an existing diagram') and enumerates exactly what the summary contains: title, workspace, element count, last-updated time. It also explicitly disambiguates from the sibling get_diagram_scene by stating it does NOT return raw scene data, so an agent can pick between the two 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?

The negative clause 'Does NOT return the raw scene data' implicitly routes the agent away from this tool when full scene contents are needed, effectively naming the alternative by contrast. There is no explicit 'use this when' statement or mention of prerequisites, so it stops short of a full 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?

With no annotations, the description carries the full burden. It helpfully discloses scope (workspace-wide) and the returned fields (id, title, last updated timestamp), signaling a safe read, but says nothing about pagination, result caps, ordering, or failure behavior for an invalid workspace_id.

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 with zero waste: the action and scope come first, then the return contents. Nothing is repeated 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?

With no output schema, the description usefully enumerates the returned fields, which is the main gap it needed to close for a simple one-parameter list tool. It omits pagination and empty-result behavior, so it is not exhaustive.

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 workspace_id parameter is 100% documented in the schema, including its UUID format, so the description needs to add little. It only reiterates the workspace scoping and contributes no extra syntax or constraint detail, matching the baseline for full schema coverage.

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 ('List all diagrams') plus scope ('in a workspace'), which cleanly separates it from write siblings like create_diagram or delete_diagram. It does not name any sibling explicitly, so it falls short of full differentiation.

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 by the verb and the name; there is no statement of when to prefer this over get_diagram_summary, get_diagram_scene, or list_folders, nor any prerequisite or exclusion guidance. Adequate but leaves alternatives 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 full behavioral burden. It usefully discloses the return shape (id, name, parent_folder_id), which compensates for the missing output schema, but says nothing about pagination, ordering, empty results, or required permissions for a read-only listing.

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, each earning its place: purpose, return shape, and downstream usage. No filler or 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?

For a simple one-parameter read tool with no output schema, the description covers purpose, return fields, and usage adequately. Only minor gaps remain around result ordering or size limits.

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% and there is a single documented workspace_id parameter, so the schema already does the work. The description adds no format or constraint detail beyond it, making the baseline 3 appropriate.

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 ('List all folders in a workspace') and goes further by naming the exact fields returned. An agent can distinguish it from create_folder and list_diagrams without opening any 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?

The final sentence gives downstream guidance ('Use folder ids when creating diagrams inside a specific folder'), which implies the why but not an explicit when-to-use-vs-alternatives rule. No exclusion conditions or prerequisites 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?

No annotations are provided, so the description carries the full behavioral burden. It signals a read-only enumeration and describes the returned fields (id, name), but says nothing about pagination, result limits, or ordering for accounts with many workspaces.

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 with no filler, ordered as purpose, return value, then usage cue. Every sentence earns its place and the most important information is front-loaded.

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 output schema and no annotations, the description usefully fills the gap by naming the returned fields and explaining why the tool matters in the workflow. Only pagination/limits remain unspecified, which is a minor omission for a simple list tool.

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, which is the baseline-4 case; there is nothing for the description to clarify beyond what the empty schema already shows. The mention of workspace_id correctly refers to output, not an input.

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 with scope: "List all workspaces in your CanvasKeep account." The purpose is unambiguous and an agent can immediately tell it apart from create_workspace by the 'list' verb, but the description never explicitly contrasts itself with any sibling, so it stops 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?

"Use this first to find the workspace_id needed by other tools" gives clear sequencing guidance and names the reason to call it. There are no explicit when-not-to-use conditions or named alternatives, but for a prerequisite lookup tool the context is effectively complete.

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 well: it flags destructive overwrite semantics, states that any omitted element is deleted, documents the isDeleted escape hatch, explains the version/versionNonce bump needed for open editors, describes container/binding relationships, and warns that unsaved browser-tab edits may overwrite the save. That is exactly the mutation-risk and side-effect context an agent needs.

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 replace-semantics are front-loaded and the IMPORTANT marker flags the destructive behavior early. The paragraph is dense and a bit long, but each sentence — versioning, container/binding structure, files/appState retention, concurrency caveat — carries actionable information rather than filler.

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 4-parameter mutation tool with no annotations and no output schema, the description covers destruction, preservation, and concurrency risk thoroughly. The only gap is that it never says what the call returns, which matters slightly since no output schema exists.

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%, so the baseline is 3, but the description adds genuine meaning beyond it: elements must be the complete array rather than a partial patch, files/appState are preserved when omitted, and it explains the internal structure (containerId, startBinding/endBinding, boundElements) that the flat schema does not convey.

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 — overwriting a diagram's scene with a full Excalidraw elements array — and scopes it to manual layout/precise edits, which cleanly separates it from the read-oriented sibling get_diagram_scene. An agent can distinguish it from generate_diagram 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?

Gives explicit use context ('manual layout and precise edits: moving, restyling, relabeling, adding or removing specific elements') and a required workflow prerequisite ('Always call get_diagram_scene first, modify that array, and send back EVERY element'). It does not name when to prefer generate_diagram instead, so the alternative-routing is incomplete for 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 discloses only that the operation is a rename; it says nothing about required permissions, whether the change is reversible, whether the title must be unique, or what happens on conflict. For a mutation tool with zero annotation coverage this is a real gap.

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 short sentence with the resource and scope front-loaded and zero filler. It is efficient, though it is so terse that it verges on under-specification rather than optimal structure.

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 very simple: two required string parameters, 100% schema coverage, no output schema needed. The description is complete enough for an agent to invoke it correctly, with the only shortfall being behavioral context a rename operation would ideally carry.

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% (both diagram_id and title are documented in the schema, including the 1-200 length bounds), so the baseline is 3. The description adds no syntax or format detail beyond what the schema already states.

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 (update/rename) and resource (diagram's title), and the parenthetical '(rename it)' sharply narrows the scope to title-only, which distinguishes it from siblings like save_diagram_scene or create_diagram. It does not name any sibling explicitly, so it stops 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?

The description says nothing about when to choose this tool over save_diagram_scene or create_diagram, nor any prerequisites or conditions of use. It is implied from the name, but no guidance is written.

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