Assign Entities To Topics

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

With no annotations, the description carries the full burden; it does disclose the matching strategy ('lightweight lexical', i.e. approximate rather than semantic) and the field requirements per entry, which is real behavioral value. It omits the one behavior with real consequences: max_entities_per_topic defaults to 12, so results are silently truncated, and nothing says what happens when a topic has more entities than the cap or whether any existing assignment is overwritten.

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 terse sentences, front-loaded with the action and method before the field requirements; nothing is padded. The second sentence is dense but functional, listing exactly the fields the schema does not name.

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?

An output schema exists, so return values need not be described, and the entry-field requirements compensate for the empty schema descriptions. The remaining gap is the undocumented max_entities_per_topic truncation and the absence of any note on deduplication or conflict handling for repeated assignments.

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 0% and the schema only says 'array of object', so the description's enumeration of required topic fields (id, label, score, size, keyphrases) and entity fields (name, optional id, weight, importance_score) adds substantial meaning. But the third parameter, max_entities_per_topic, is never mentioned anywhere, and it is the parameter most likely to change output.

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?

States a specific verb and two resources: 'attach entities ... to topics', plus the matching method ('lightweight lexical matching') and the upstream source ('topics from extract_topics'). An agent can tell what it produces without opening the schema. It does not, however, distinguish itself from the sibling cluster_entities, so it stops 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?

Usage is implied through the pipeline reference to extract_topics (topics must come from there) and the stated required fields. There is no explicit when-to-use/when-not-to-use guidance and no mention of cluster_entities as an alternative for grouping entities, leaving the agent to infer when this lexical approach is the right choice.

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