review_draft

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

No annotations exist, so the description carries the full burden and does so richly: it describes the output structure (must_fix / worth_fixing / consider with sentence-level notes plus positives) and enumerates the concrete checks performed (unsupported figures/quotes, quotes over 15 words, missing attribution, stock AI phrasing, weak openings, hedging stacks, passive density, flat rhythm). This is well beyond what the schema provides.

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?

Front-loads the purpose and the critical constraint ('Never rewrite it') before elaborating the check list. The final line ('Returning a rewritten draft defeats the purpose') is a mild repetition of the earlier prohibition, costing a little efficiency.

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 two-parameter, no-annotation, no-output-schema tool, the description covers purpose, inputs, output categories, and the full review rubric. The only shortfall is the unclear handling of the optional `facts` parameter and what happens when it is null.

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 0%, so the description must compensate, and it partially does by explaining that `draft` is the human-written text and `facts` comes from fetch_article_facts. It does not clarify that `facts` is optional/defaults to null or the expected fact object shape, leaving a gap given the zero coverage.

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+resource ('Read the writer's draft and say where it is weak') and immediately distinguishes itself from the sibling humanize_text by forbidding rewriting. The 'Step 6' marker and reference to fetch_article_facts position it precisely in the workflow.

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?

Clearly says to pass the human-written draft and the facts from fetch_article_facts, and explicitly warns 'Never rewrite it' / 'Returning a rewritten draft defeats the purpose.' It doesn't name an alternative tool to use instead when a rewrite is actually wanted (e.g. humanize_text), but the boundary with the rewrite siblings is strongly implied.

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