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

Goes well beyond the readOnly/idempotent/non-destructive annotations: discloses the partner-or-enterprise key requirement, that the response is complete and non-streaming, and that identical brief+filters are cached for 24h with stable citations. Those are exactly the operational facts an agent needs before invoking an expensive composite call.

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 what the tool does, then the pipeline stages, then the streaming caveat, caching, and auth in descending priority. Roughly five dense sentences with little waste; the 'Returns the complete result (non-streaming)' clause is slightly redundant with the SSE sentence but still earns its place.

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 pipeline stages effectively communicate what comes back despite no output schema, and auth/caching are covered. But for a 13-parameter tool at 8% schema coverage, the description leaves the entire filter surface unexplained, which is a material gap 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 8% across 13 parameters — only 'brief' is documented. The description adds no meaning for the filter parameters (countries, hsCodes, employeeRange, certifications, foundedAfter/Before, businessType) beyond a passing reference to 'brief + filters,' so an agent must guess at their semantics, formats, and interactions.

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?

Specific verb and resource: 'One-shot deep research' that runs a named pipeline (shortlist, dossier with due-diligence signals, AI comparison, recommended next step). The phrase 'full pipeline in a single call' distinguishes it from the granular siblings like match_suppliers_by_brief, get_red_flags, and compare_suppliers without needing to open a 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?

Explicit routing condition: use it 'when your agent cannot consume the /mcp/deep SSE stream,' which names the alternative and the condition selecting this tool. It also notes caching makes repeated calls cheap. It does not, however, say when to prefer this over the sibling pipeline pieces (e.g. match_suppliers_by_brief or compare_suppliers) for cheaper partial work.

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