scf_get_vendor_assessment

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

Annotations declare readOnlyHint=true, which already covers the safety profile, so the description only needs to add value beyond that. It does so by disclosing the response content — services_used, data_role, RAG status, recommendation, full report fields, and research sources — giving the agent a concrete expectation of what 'full detail' means. There is no contradiction between the description ('Get') and the read-only annotation. It stops short of describing failure behavior or data freshness, but for a read operation the disclosed detail is solid.

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?

A single sentence of roughly 24 words, front-loaded with the verb and resource ('Get one vendor AI assessment by ID') followed by a colon-delimited enumeration of return contents. There is zero filler, and the detail list is information-dense and well structured. Every word 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?

For a simple read-by-ID tool with all three required parameters fully documented and a readOnlyHint annotation, the description is nearly complete. The enumeration of return fields partially compensates for the missing output schema. The only notable gap is the absence of guidance on how this tool differs from scf_get_latest_vendor_assessment and scf_get_vendor_assessment_status, which is already penalized under usage guidelines rather than here.

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 100%, with each UUID parameter having a 'format' and an explicit provenance hint (e.g., 'obtain from scf_list_vendors', 'obtain from scf_list_vendor_assessments or the trigger response'), so the schema already carries the documentation burden. The description adds no parameter-level semantics beyond the phrase 'by ID', which confirms assessment_id is the primary selector. Baseline 3 is appropriate when the schema does the heavy lifting.

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 names a specific verb and resource ('Get one vendor AI assessment by ID') and enumerates the detail fields returned (services_used, data_role, RAG status, recommendation, full report fields, research sources), making the purpose unmistakable. The phrase 'by ID with full detail' hints at differentiation from close siblings like scf_get_latest_vendor_assessment and scf_get_vendor_assessment_status, but it does not explicitly name them. This is clear, though slightly short of the explicit sibling differentiation that earns a 5.

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?

Usage context is implied rather than stated: 'by ID' signals this tool is for when a specific assessment identifier is already known, and the assessment_id parameter description ('obtain from scf_list_vendor_assessments or the trigger response') provides some navigational guidance. However, there is no explicit when-to-use versus scf_get_latest_vendor_assessment or scf_get_vendor_assessment_status, and no exclusions or alternatives are named. The agent must infer the selection criteria from the tool name and parameter provenance hints.

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