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

Annotations already declare readOnlyHint=true, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral detail beyond that: it merges duplicate findings across evaluators, computes a health score, and sorts a fix-first table, which tells the agent the output is transformed rather than a passthrough. It leaves 'exportable' ambiguous (returned markdown vs. file write), which is a minor gap given the readOnly annotation.

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, front-loaded with the action and output format, then the mechanics. The leading 'Pro.' token is unexplained noise that does not earn its place, but everything after it is tight and informative.

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 read-only aggregation tool with no output schema, the description covers input expectations, internal processing (merge, health score, sorting), and output form (scored, exportable markdown). The only missing piece an agent would want is whether the markdown is returned inline or written to a path, which matters for follow-up calls.

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. The description earns above baseline by explaining the domain semantics of the findings fields – heuristic numbers 1–10, severity 0–4, effort S/M/L, evaluator – and, importantly, that 'evaluator' drives duplicate merging, which the schema alone 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: 'Build a scored, exportable markdown report from heuristic evaluation findings.' It is clearly differentiable from sibling heuristic_worksheet (which produces the findings) because this one consumes findings 'you have written'. It stops short of explicitly naming the upstream sibling, so the routing is implied rather than stated.

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 heuristic evaluation findings you have written' implies this is a downstream/publish step after authoring findings, which is useful context. But there is no explicit statement of prerequisites (minimum findings, required fields beyond the schema), no when-not-to-use, and no named alternative for related tasks.

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