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

Annotations declare destructiveHint=true and openWorldHint=true, but the description says nothing about what is written or destroyed, that sources are sent to an external inference provider requiring consentExternalProcessing, or that a run ID and idempotency key are involved. For a tool flagged destructive and open-world with no output schema, this omits the behavioral facts an agent most needs.

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 tight sentences, front-loaded with the comparison and followed by the trace targets. No filler, no restatement of the title.

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 enumerated artifact types partially compensate for the missing output schema by signaling what comes back, and the nested inputs are self-described in the schema. However, with a destructive, open-world, externally-processing tool, the description should at minimum surface the consent/processing model and the role of prior-run reuse.

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 67% and the description only echoes the rfp/transcript inputs while "exact source quotes" loosely implies quote-level grounding. It adds nothing about sourceFields, sourceRunIds (reusing prior agent runs), consentExternalProcessing, or idempotencyKey, which are the parameters most likely to be misused.

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?

Uses specific verbs (compare, trace) on a clearly named resource pair (transcript vs. RFP requirements), and the four enumerated artifact types (commitments, contradictions, gaps, follow-up questions) make the output shape concrete. It does not name or distinguish itself from plausible siblings like xscore-bid-evaluation or xrfp-drafter, so an agent must infer the boundary.

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?

"Compare what was said with RFP requirements" implies the precondition of having both a transcript and an RFP, but there is no explicit statement of when to use this versus bid scoring, RFP drafting, or the rfp_to_bid_review workflow. No exclusions or alternatives are given, leaving routing to inference.

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