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

Adds genuinely non-structural behavior: the 500-row cap per call, that quota is consumed only after the file is built successfully, and that `full` dumps can break MCP clients. These go beyond the annotations (readOnlyHint=false, idempotentHint=false) by explaining the cost/size semantics. It stops short of describing response shape or error behavior.

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?

Dense but front-loaded: format and row cap first, then the `fields` tiers, then the quota note, then the routing alternative. Every clause carries information, though the field-preset sentence is long enough to require a second read.

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 15-parameter, zero-required export tool with no output schema, the description covers the decisions that matter (which preset, what format, size ceiling, quota). Filter parameters are left to the fully documented schema, which is reasonable, but filter combination behavior is not addressed.

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 already 100%, so the baseline is 3, but the description adds useful aggregate semantics by naming the concrete column set behind each `fields` preset (e.g. `summary` adds location, PKD, latest revenue/profit) rather than just restating the enum.

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+resource ('Bulk file export of companies matching filters') plus the three output formats, and clearly distinguishes this from search_companies by pointing at the alternative for short email lists. An agent can select it without opening the 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 explicit guidance on which `fields` preset to choose, warns that `full` often exceeds MCP client limits, and names the alternative path ('for a short list of emails after search_companies, use search with fields=contacts_only instead'). When-to-use and when-not-to-use are both present.

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