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

With no annotations, the description's opening 'Read-only' is genuinely useful, declaring the operation is non-mutating. It also compensates for the missing output schema by listing the columns. However it says nothing about what happens with an invalid or un-run search_id, whether the result is a file handle or inline CSV, or any size limit.

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?

Two short sentences with the read-only constraint front-loaded and the column list following. The dense column enumeration earns its place as substitute output documentation, though it reads as a raw dump.

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 column list usefully stands in for the absent output schema, but for a one-parameter export tool the description omits the critical link between the parameter and the search, plus any failure or scale behavior. Adequate, not complete.

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 single parameter search_id has 0% schema description coverage and the description never mentions it — not its UUID format, not that it identifies the SDR search whose companies are exported. The description must compensate at low coverage and does not.

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 (export a CSV of every company the search found) and enumerates the columns returned. It implicitly separates itself from the sibling sdr_export_people_csv by scoping to companies, though it never names that sibling explicitly.

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?

No guidance on when to use this versus sdr_export_people_csv, sdr_get_search, or sdr_company_detail, and no mention of preconditions such as the search existing or having completed. The agent must infer usage entirely from the name.

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