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

Adds substantial context beyond the annotations: the Admin-only permission requirement, the consumption of one weekly allowance update, the idempotency-key retry semantics, and the guarantee that a retry neither starts a second job nor double-charges the allowance or daily cap. This is exactly the operational cost and auth detail the readOnlyHint/openWorldHint annotations cannot convey; the annotation idempotentHint=false reflects raw call behavior, while the description correctly scopes idempotency to key reuse.

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 action and its precondition, and the operational constraints are packed densely. The final sentence ('It starts no second job and uses no allowance or daily cap a second time') largely repeats the preceding idempotency sentence, which is minor redundancy rather than noise.

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 mutation tool with an output schema, the description covers permissions, cost, precondition, and retry safety, so return values need no explanation. The one gap is failure-mode behavior: it does not say what the caller gets back if the competitor already has research or if the allowance is exhausted.

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 description coverage is 100%, so both competitor_id (sourced from list_competitors) and idempotency_key are already fully documented in the schema. The description restates the idempotency-key contract and nothing more, 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 ('Starts the first research on one core competitor') plus the eligibility precondition ('that has none yet'), which no sibling tool performs. An agent can distinguish this from read-only siblings like get_competitor or list_competitors without opening either 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 clear usage context: it applies to a core competitor with no existing research, it requires Admin, and it consumes one weekly research allowance update. No alternative tool is named, but no sibling performs research at all, so there is no routing ambiguity to resolve. It also does not say what to do if the competitor already has research beyond noting no second job starts.

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