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

Annotations mark it non-readonly, non-idempotent, non-destructive but say nothing about persistence or cost. The description adds two genuinely useful behavioral facts: it is a single LLM call, and it does NOT mutate the article in place — the caller must swap the returned section back in. That non-persistence disclosure is the key behavior an agent needs and is not derivable from the annotations.

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?

Tight, front-loaded, and every clause carries signal: purpose, input source, instruction meaning, cost, return contract, and workflow order. The final key-enumeration list is mildly redundant with the schema, which keeps it from a 5.

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 12-parameter tool with no output schema, the description covers the essentials: what it does, what to pass, that it returns a replacement section, and that the caller must persist it. It does not document error/permission behavior or rate limits, but given the closed-world, non-destructive annotation profile, nothing critical for correct invocation is missing.

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 75%, so most parameters are already documented structurally; the schema spells out `urls`, `articleType`, `useExternalLinks`, and the section sub-keys. The description adds meaning for `instructions` ('what to fix or change') and enumerates the accepted `section` keys, but leaves other inherited builder params (site, prompt, locationId) unexplained. 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+resource ('rewrite a single section of a written article') and scopes it precisely against the sibling family (write_from_outline produces the section, regenerate_outline is a different granularity). The title 'Builder: rewrite one section' reinforces it without being a tautology. An agent can distinguish this from write_article_now or update_article without opening any schema.

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?

Names the input source ('pass the section object from write_from_outline') and the downstream step ('swap it into the article's sections before publish_article_from_builder'), giving a clear workflow position. It lacks an explicit 'when not to use' or named alternative (e.g., when to edit manually vs regenerate), so it stops just short of a 5.

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