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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), and the description goes well beyond them: it discloses the data provenance (two 2026 studies plus Suara's own index and client data), that disagreements are surfaced rather than resolved, and that results are in the city's local time. That is exactly the behavioral context an agent needs to describe the answer honestly.

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-loaded with the use case, then the return behavior, then the exclusions — a logical order. It is a single dense sentence-chain that's somewhat run-on, but each clause (cities, time zone, source agreement, own data, exclusions) carries information rather than 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?

There is no output schema, and the description fully compensates by explaining what comes back: local-time windows where two studies agree, explicit disagreement surfacing, and supplementary Suara measurements. Combined with the explicit exclusions, an agent has everything needed to call it and set expectations.

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%, so baseline is 3. The description still adds real value by closing the open-ended city parameter into an explicit supported set (plus accepting 'one of those countries'), which the schema only gestures at with 'e.g.' examples. It does not clarify how category interacts with the restaurant-index data source, which keeps it from a 5.

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?

Opens with a specific trigger verb plus resource ('when to post on Instagram, Facebook or TikTok') and enumerates the exact supported cities. No sibling tool (insights, posts, audio, holiday) overlaps with this function, so the agent can route on it immediately.

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?

Gives both sides explicitly: use it when someone asks about posting times in the listed geos, and 'Do not use it for other cities, for a specific account's own best time, or to promise results.' The exclusion of 'a specific account's own best time' implicitly points to per-account tools like my_instagram_insights.

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