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

Adds real behavioral context beyond the annotations: 'Free (no credits)', ordering guarantee ('Best first'), and that each result carries its pattern and estimated percentile. Annotations already cover safety profile (non-destructive, non-read-only, non-idempotent), so this complement is enough, though it doesn't say whether generated hooks are persisted server-side.

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 what is produced and that it is free, then moves to prerequisites and next actions. A few parentheticals add length but each carries usable information; no filler sentences.

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 annotations, full schema coverage and an output schema present, the description only needed to cover prerequisites and the cross-tool workflow, which it does. Minor gap: no mention of whether results are stored or how failures surface, but that is close to negligible for a generation tool with an output schema.

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% and documents all four parameters including defaults and the enum, so the baseline is 3. The description only restates that topic, audience id and platform aim the output; it adds no format or constraint detail beyond the schema.

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 concrete verb and resource ('Write hooks — the first line or first 2 seconds of a post') and immediately describes the output shape (score 0-100, pattern, percentile, rationale, best first), which distinguishes it from the similarly named hooks_score sibling that evaluates rather than writes.

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?

Explicitly says to call brand_read first if brand_profile is empty, names the steering inputs (topic, audience id from brand_profile, platform), and gives the follow-up action: pass the best hook as 'hook' to studio_generate. When, prerequisites, and next step are all covered.

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