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

Goes beyond the readOnly/openWorld annotations by naming what is rejected (status, budget, bids, campaign creation) and stating the return is the platform's raw JSON, which tells the agent to analyse the payload elsewhere. Doesn't mention rate limits or the per-platform pagination/merge behaviour that the schema carries.

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?

Two sentences, front-loaded with the core action, then the reference pointer, then the write rejection. Nothing is repeated or padding.

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 9-parameter, open-world passthrough tool with no output schema, the description supplies the essential mental model: one request, raw platform JSON, writes are refused, consult the reference tool. Missing only rate-limit/error behaviour and the out/project_id persistence workflow, the latter being covered by the 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 78% and the schema itself documents platform bases, GAQL for Google, body for POST-style reads, and cursor paging, so the description needs little more. It adds no parameter-level meaning of its own beyond implying platform-specific endpoint choice via the reference tool.

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 ('Runs one read-only request against a connected ad account and returns the platform's JSON'), and explicitly names the sibling composer_ads_reference as the source of endpoints/fields, which separates this tool from documentation lookup.

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 the routing rule to composer_ads_reference for endpoints and fields, plus a hard exclusion ('Writes ... are rejected'). It doesn't cover the account-discovery prerequisite (that lives only in the account_id schema) or comparisons against other siblings, but the when-to-use guidance is clear.

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