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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered structurally. The description adds a useful scope caveat (not a substitute for generation), but omits what is actually compared, what a failure means, and what the output looks like.

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 padding, and the scope caveat is placed last where it qualifies the verification claim. 'Hashes' is the only word that could be tightened for precision.

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 carries the burden of explaining what a check result looks like (pass/fail, mismatch detail), which it does not. For a simple diagnostic it is adequate, but an agent cannot predict the response shape.

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 is 4; there is nothing for the description to compensate for, and it correctly implies no inputs are needed.

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 ('Verify') and resources ('Structurizr and PlantUML hashes'), and adds a distinguishing caveat that it does not replace real generation, separating it from generate_c4/render_structurizr. The term 'hashes' is left ambiguous (binary hashes? version fingerprints?), keeping it 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 line 'does not replace a real generation' implies this is a pre-flight/sanity check rather than a substitute for generate_c4, but it never explicitly says when to call it or what to do with the result. Usage is inferable but not 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?

Annotations declare readOnlyHint=false and destructiveHint=false, and the description usefully adds that outputs include a viewer and a hashed manifest and that rendering is 'transparent' (traceable). However, it does not say that artifacts are written to a project-named folder, whether existing output is overwritten, or what happens on oversized models — meaningful gaps for a non-idempotent write tool with openWorld=false.

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 dense sentences, with the generation action and the artifact list front-loaded and no filler. Slightly jargon-heavy but every clause carries 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?

Given a deeply nested required 'model' with people, systems, containers, components, codeViews and relationship limits, and no output schema, the description says nothing about model structure or validation constraints. The artifact and return-value side is covered adequately, but the input-side burden is not.

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 only 33% — only 'project' (output folder name) is documented, while the large 'model' object and 'levels' array are not. The description partially compensates by tying the tool to an 'explicit architecture model' and enumerating C1–C4, which the agent can map to the levels enum, but it never explains the model's required shape (focalSystem, systems/containers/components/codeViews).

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 (generate) and concrete artifacts (Structurizr DSL/JSON, C1–C4 diagrams, SVG/PNG, viewer, hashed manifest), which is far more informative than the title alone. It doesn't distinguish itself from the sibling render_structurizr, which likely also produces diagrams, so the agent can't tell from the description which one to pick.

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 'from an explicit architecture model' implies the model must be supplied rather than inferred, but there is no explicit when-to-use, no when-not-to-use, and no mention of when render_structurizr would be the better choice. The agent is left to infer the routing decision.

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?

The annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful context about returned content types and an output-root restriction, but says nothing about error behavior, path resolution, or what happens when a path falls outside the root.

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 compact sentence that front-loads the return types and appends the key scoping constraint. There is no redundant or wasted wording.

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 is adequate about what it returns and its boundary. However, it leaves the crucial path semantics underspecified, which is the main thing an agent needs to invoke it 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 coverage is 0% and the sole parameter, path, has no description in the schema. The phrase 'restricted to the output root' hints at path scope, but it does not explain whether the path is relative or absolute, what format is expected, or how extensions map to artifact types.

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 ('Return') and enumerates the resource types returned: PNG images, editable sources, or manifests. It is clearly a read operation and distinguishable from the generator/renderer siblings, though it does not explicitly name 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 no explicit when-to-use guidance or alternatives. 'Restricted to the output root' is a scope constraint, not usage advice, so an agent must infer that this tool is for fetching already-generated artifacts.

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=false, destructiveHint=false, openWorldHint=false, so the safety profile is partly covered. The description adds real behavioral context beyond that: it rejects executable directives and external references, and requires the DSL be self-contained — which explains the openWorldHint=false claim in practical terms. It does not mention rate limits, failure modes, or where output lands.

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, then the routing rule, then the constraint. No filler or restatement of the name/title.

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?

No output schema exists, but 'Render real C1-C3 images' plus the 'project' output folder param conveys the return well enough. The main remaining gap is that the DSL dialect/format an agent must write is never characterized beyond what is rejected.

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 50%: 'project' is documented as the output folder name, while 'dsl' has only min/max length. The description partially compensates by constraining what the DSL may contain (no executable directives, no external references, must be self-contained), but gives no syntax, format, or size guidance. Baseline 3 is appropriate given partial 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?

Specific verb+resource: "Render real C1-C3 images from self-contained DSL" tells the agent exactly what is produced and from what input. It also implicitly scopes out C4 rendering, which the next sentence makes explicit, so it is distinguishable from generate_c4.

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 C4 work to the sibling: "Use generate_c4 with codeViews for C4." That is a clear alternative-plus-condition. It does not state when-not to use this tool in any other sense (e.g. size limits, when to prefer read_artifact for existing renders), so it falls short of full 5 coverage.

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