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

Annotations already declare readOnlyHint/destructiveHint false, and the description reinforces the no-mutation guarantee. Beyond annotations it describes the shape of the produced findings, which is valuable given there is no output schema, though it does not cover failure modes for malformed or unrecognized report text.

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, front-loaded with the core action and output fields, followed by a single usage/safety note. No repetition or 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 read-only parser with no output schema, the description covers input provenance, output fields, and non-mutation adequately. It falls short only on error/format-validation behavior, which an agent might want before passing arbitrary report text.

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 100% schema description coverage, the schema already documents all four parameters, including the exactly-one-of constraint between report_text and report_pdf_base64. The description only adds the note that HTML or PDF sources are accepted; 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 (convert/parse) and resource (extracted text from a QualityMax-style mobile audit report) and enumerates the structured output fields (ID, severity, surface, breakpoints, root cause, fix prompt). This distinguishes it from siblings like get_mobile_audit_evidence, render_mobile_audit_report, and list_mobile_audits, which retrieve or render rather than parse.

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 a downstream usage hint ('use the result to create or link follow-up work') and a firm exclusion ('never changes project data'), but it never says when to call this instead of adjacent tools like get_mobile_audit_evidence or render_mobile_audit_report, nor what prerequisites the report text must satisfy.

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