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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds real behavioral context: disputes are durable, the creating client cannot manufacture independence via source_model, locked subjects stay locked, and the server independently re-validates structural writes. It stops short of describing success/failure outcomes, but the added context is substantive.

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?

The purpose is front-loaded, but the majority of the text is generic classification policy ('Material, arrangement/grouping, state/condition... belong in attributes') that explicitly applies to creating, selecting, and relating as well, not to invoking this tool. That bulk dilutes the call-relevant guidance.

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 non-idempotent-looking but annotation-marked idempotent mutation with no output schema and very low parameter documentation, the description covers the dispute mechanics but omits the evidence payload shape, what a 'strict descendant type' verification returns, and most parameter semantics. Adequate but with clear gaps.

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 only 17% across 6 parameters, so the description must compensate and largely does not. It adds meaning only for source_model ('stable model identity' + the independence constraint), leaving target_subject_type, reason, evidence, and evidence_fingerprint unexplained in both schema and description.

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 first sentence gives a concrete verb+resource ('submit an evidence-backed refinement to a strict descendant type') on a subject's creation proposal, which is distinct from affirm_subject_classification or reopen_subject_classification. However, it never explicitly contrasts itself with those siblings, so an agent must infer the routing.

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?

The description supplies domain conditions (a differing authenticated client opens a durable dispute; a locked subject is not reopened), which implies when this tool applies. But it never states when to use it versus affirm_subject_classification, reopen_subject_classification, or enrich_subject, so the selection guidance is implied rather than explicit.

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