Check local engines

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.