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

The description adds substantial behavior beyond annotations: one model creates a candidate, agreement by two distinct models automatically moves the subject, confirms and locks it, and a locked subject is not reopened by later opinions. It also warns that the server independently validates structural writes. This gives an agent a clear mental model of side effects, which is especially valuable because the annotations only provide idempotent/destructive hints.

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 first sentence is front-loaded and states the core action. The later policy sentences about semantic heads, modifier categories, and compound-type exceptions are relevant and earn their place for this domain. The description is longer than average but not bloated, and the structure moves from mechanism to vocabulary rule to server enforcement logically.

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 description covers the consent/locking mechanism, vocabulary constraints, and server-side validation well, which is a lot for a proposal tool with no output schema. It leaves a small ambiguity: what happens while a candidate is pending or if the two-model agreement condition is not met. Overall, an agent has enough to call it correctly, but not every outcome is explicit.

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 only 17%, so the description must compensate. It richly explains target_subject_type with the strict-descendant, semantic-head, and modifier guidance, and source_model is already described in the schema. However, reason and especially evidence_fingerprint are not meaningfully defined beyond the schema, and evidence is only vaguely described as evidence-backed, leaving a gap for a low-coverage tool.

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 opens with a specific verb and resource: submit an evidence-backed refinement to a strict descendant type. It separates this from a plain type selection or affirmation by emphasizing that one independent model creates a candidate, which is a distinct action from affirming or moving a subject. It does not explicitly name a sibling alternative, so it falls short of 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?

The description gives clear context for when to use this tool: before proposing a subject type, identify the semantic head and modifiers, and avoid using material, arrangement, quantity, colour, size, location, or purpose/use in type names. It also explains when a compound may remain a distinct type. It does not explicitly state 'use X instead for affirmations' or give a formal when-not-to-use list, but the guidance is strong.

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