competitor_probe_classify

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

With no annotations, the description discloses the side effects of each classification value, which is essential for a mutation tool. It also clarifies what is modified ('probe JSON only' for non-direct) and states the return value. This gives the agent transparency into the operation's impact.

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 description is three sentences that pack in the action, side effects, usage constraints, and return value without any filler. It is front-loaded with the verb and resource.

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?

The tool has no output schema, but the description explicitly states the return shape ('Returns { candidates } — the updated full candidate list'). It also provides the state prerequisite and per-domain call limit. For a 4-parameter tool without annotations, this is a complete and self-contained description.

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?

The schema already provides descriptions for all four parameters (100% coverage), so the baseline is 3. The description adds important context for the classification values by explaining that 'similar' and 'not_relevant' update the probe JSON only, which is implied but not explicitly stated in the schema. This adds value beyond the schema, but not significantly for other parameters.

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?

The description clearly states the tool's function: 'Classify a discovered (or manually added) competitor candidate.' It differentiates from sibling tools like competitor_probe and competitor_add by specifying the three-way classification and its distinct side effects ('direct' seeds a BrandCompetitor row; 'similar' and 'not_relevant' update the probe JSON only).

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?

It provides explicit usage prerequisites: 'Call once per domain' and 'Probe must be in completed state first.' It doesn't name alternative tools but implies this is the classification step after competitor discovery, which is clear given sibling names like competitor_probe and competitor_probe_status.

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