lint_diagram

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

No annotations exist, so the description carries the full burden. It communicates that this is a non-mutating review and lists what is checked, but it does not disclose the result format, whether failures are reported, or any side effects. An agent cannot predict what the tool returns after invocation.

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 purpose, followed by a compact list of the exact checks. No filler words or redundant schema 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 tool has no output schema and no annotations, so the description must cover both invocation and expected result. It adequately names the checked aspects, but it leaves a critical gap by not describing what the agent receives after the review is complete, such as a report, exit codes, or detailed issues.

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?

With schema description coverage at 0%, the description must compensate. It only vaguely implies that 'path' refers to a .drawio file via 'de un .drawio'; it does not specify path resolution, absolute vs relative, or any constraints. The single parameter is just barely covered.

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 performs an 'objective review of a .drawio' and enumerates the exact checks (overlaps, edges crossing nodes, isolated nodes, proportion). This distinguishes it from the diagram-generation siblings like build_diagram and render, though 'doctor' may overlap.

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 naming the validation concerns, so an agent can infer when to run it. However, it does not explicitly state when to use this tool over alternatives such as 'doctor', and it gives no exclusions or preconditions.

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