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

Annotations already declare readOnlyHint and openWorldHint, but the description adds substantial non-obvious behavior: searches without a country filter scan all 19 partitions, are slower, and cap at 10 results; cross-country NACE/employee_count filters error; and results include ranked candidates with confidence scores and matched_fields. This goes well beyond safety annotations.

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 purpose and primary usage, then caveats and return shape. Every sentence is informative, though the description is long and dense; it could trim some output-format detail without losing value.

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 10-parameter search tool with no output schema and rich annotations, the description supplies the key operational context: usage alternatives, performance caveats, error behavior, and return structure (data[], match block, total_count, has_more, next_cursor). Missing parameter-specific details are covered by the schema enums/defaults, so the definition is complete enough for correct invocation.

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 30%, so the description must compensate. It clarifies q (name, registry identifier, address fragment), country (ISO alpha-2, multi-country comma-separated), and NACE (requires country), but leaves sort, limit range, cursor, status, include, and registered_date filters unexplained, so several parameters remain semantically thin.

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: 'Search FirmaDB's European company index' and names the supported query modes (name, registry identifier, address fragment). It explicitly distinguishes from firmadb_get_company by telling the agent to use this before get_company when no registry_id is available.

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 when-to-use ('DON'T have a registry_id but you have a name, address, NACE code, or industry term') and when-not/alternative ('Use BEFORE firmadb_get_company when the user gave you a name...'). It also adds practical routing rules such as filtering by country and disambiguating common names.

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