feature_separate_eval_run

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

With no annotations provided, the description carries the behavioral burden. It does well by disclosing that data is sent to a configured Judge, that patent records trigger an external PatSnap call requesting only CLMS, that results are persisted, and that network access must be approved. It does not cover all possible side effects or failure behavior, but the most consequential behaviors are transparent.

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 description is three tightly written sentences. It front-loads the core purpose, then provides the essential process detail, and ends with an important safety condition. No repeated or redundant information is present.

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 purpose, the Judge interaction, the patent-network special case, persistence, and the allow_network constraint. Given the tool has 7 parameters, no annotations, and sibling tools for status/checking, it would benefit from explaining keep_pending and the two max-feature parameters, and from routing the agent to the correct sibling when appropriate.

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 0%, so parameter semantics must come from the description. It adds meaning for allow_network, patent_number, judge_model, and implicitly record_id by mentioning decompositions, Judge, PatSnap, and the confirmation condition. However, keep_pending, max_feature_density, and max_features_per_claim remain unexplained, so there are clear gaps.

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 clearly states the tool's job: 'Evaluate one decomposition and return its human report and persisted result.' This is a specific verb and resource, and the mention of a returned report distinguishes it from the likely status/check siblings. It stops short of explicitly contrasting itself with those siblings, so it gets a 4 rather than 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 implies when to use the tool: when a decomposition needs to be evaluated. It gives a concrete conditional for patent records and an explicit safety rule for allow_network, which is useful. However, it does not mention the sibling tools or state when to use this tool instead of feature_separate_eval_status or feature_separate_eval_check.

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