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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real context: the references were written for Creatify's own agent, so where they use `requests` or the google-ads library with a token from context.json, the same method/path/params (Google: the GAQL) go through composer_ads_read with the token omitted. It also discloses that write/launch/action requests are unsupported. Minor gap: no indication of reference size or how to enumerate topics.

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?

The purpose and the pre-query instruction come first, followed by the token/method translation rule and the limitation. Dense but each sentence carries work; the middle sentence is long and slightly tangled, which keeps it below 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 single-optional-parameter documentation-retrieval tool with annotations and no output schema, this covers purpose, preconditions (read SKILL.md first), how to apply what is returned, and what cannot be done. An agent has enough to call it correctly and know what to do with the result.

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 the topic parameter is already documented with an example path and default. The description mentions 'a path from `topics`' and the SKILL.md default but adds no format or discovery detail beyond the schema, so the baseline 3 applies.

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 and resource: returns Creatify's ad-platform API reference (endpoints, fields, enums, pitfalls). It also explicitly contrasts with the sibling composer_ads_read, which is the tool that performs the actual queries, so the two are distinguishable without opening a 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?

Gives explicit when-to-use ('read SKILL.md and the platform's read reference before the first query') and when-not-to-use ('Writes, launches and action requests are not available here yet'), plus named alternatives (offer advice to the user, or point to Creatify's Ad Agent). Nothing about routing to this tool vs. composer_ads_read is left to inference.

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