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

annotations only carry readOnlyHint=true, so the description does the heavy lifting: it reveals that this mirrors the save-time gate, names the downstream error code it prevents, and discloses Space scoping plus the per-call override. What it omits is the result shape (boolean verdict vs. list of matches) and what a 'too close' response contains.

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?

Three tight sentences, front-loaded with the core behavior, then the usage trigger, then the scoping caveat. No filler and nothing buried.

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 read-only preflight check with no output schema, the agent knows why to call it, when, and how to scope it. It lacks only what a response looks like and how to act on a positive similarity hit, which is a real but minor residual gap.

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 space_id's semantics are already spelled out in the schema, so the description only restates it briefly. The description never mentions the nested businessId field or clarifies what texts accepts (single string vs. batch), leaving that entirely to the schema, so 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 action (run the similarity check), a specific resource (ad copy vs tracked competitor ads), and even the second failure mode it detects (naming a competitor). No sibling tool in the list performs competitor-copy similarity, and the description makes that scope unmistakable.

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 prescribes the timing — 'Use before creating or updating ads to avoid a 409 COMPETITOR_SIMILARITY' — which tells the agent exactly when to reach for it. It also routes space scoping to set_active_space versus the space_id override, but gives no 'when not to use' guidance or alternative tool for other preflight checks.

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