office_prepare_review

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

Annotations already declare this is a non-read-only, destructive, non-idempotent write, so the safety profile is covered. The description adds genuinely non-obvious behavior (PowerPoint renders use hidden windows) and names the outputs (hash + manifest). It does not disclose what is destroyed or overwritten in outputDirectory, which matters given destructiveHint=true.

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 tight sentences, front-loaded with the core action and followed by the render caveat and the verification instruction. No filler, though the sentence on hidden windows is slightly parenthetical to the main point.

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 it correctly enumerates the returns (PNGs/PDF, source hash, artifact manifest), which is useful. But for a 4-parameter tool with a deep contract object it leaves the contract semantics unexplained and omits how the produced evidence is later retrieved (presumably office_get_review_image) or how contract failures manifest.

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 50% and the large nested contract object (objective, criteria, powerpoint, word, excel, baseline, requiredText/forbiddenText) is entirely undocumented by either schema or description. The description never explains what contract or maxInlineImages control, so it fails to compensate for the coverage gap.

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 and artifact: creating hashed review evidence (slide PNGs or a PDF, source hash, artifact manifest) for a quality-checked draft. That is far more concrete than the name alone and distinguishes it from office_quality_check and office_finalize. It stops short of naming the sibling it pairs with for retrieving the evidence.

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 one usage instruction — inspect every slide or the complete PDF before attesting quality — which implies a verify-then-attest workflow. It does not say when to choose this over office_quality_check, office_finalize, or office_compare_files, nor any prerequisites (e.g., is the draft required to have passed quality_check first?).

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