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

Annotations already indicate the tool is read-only, open-world, idempotent, and nondestructive. The description adds behavioral insight by explaining how sector aliases are resolved (e.g., `abogados` resolves to canonical slug) and that the response includes `_meta.sector_resolved_from`. This goes beyond annotations, though it does not detail rate limits or potential response variability.

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 concise (3 sentences) and front-loaded with the core purpose. The additional detail about sector vocabulary is placed naturally, but the last sentence could be slightly more streamlined to avoid over-explaining the alias resolution, though it remains valuable.

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?

Given the tool has an output schema and clear annotations, the description covers the key aspects: purpose, sector vocabulary behavior, and geographic scope. It does not address pagination or ordering of results, which could be inferred from the `limit` parameter. For a ranking tool with clear constraints, this is nearly complete but missing an explicit statement about result ordering (e.g., by relevance).

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%, but the description adds significant value beyond the schema by explaining that `sector` is a closed vocabulary with aliases that resolve to canonical slugs, and that the response will indicate the resolution. It also clarifies that `city` is limited to Spanish cities, reinforcing the geographic constraint. This rich semantic guidance helps the agent avoid errors with non-canonical values.

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 purpose: 'Find real competitors in the same sector and city.' It specifies the criteria (identity, location, sector matching) and geographic scope (Spain only), which distinguishes it from siblings like `search_entities` or `entity_lookup` that likely have broader or different search capabilities.

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?

The description provides clear usage guidance by specifying the geographic constraint ('Spain only on the public surface') and noting that the `sector` parameter uses a closed vocabulary with aliases. However, it does not explicitly mention when not to use this tool (e.g., for non-Spain competitors or non-public data) or compare it directly to sibling tools, though the sibling context suggests differentiation from `search_entities`.

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