Find Similar Career Points

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

Goes well beyond the readOnly/idempotent annotations: deterministic zero-LLM scoring, the 0.80 cosine threshold, exclusion of retired and user_cannot_confirm points, subtraction of user-marked 'Not the same' pairs, and the keeper precedence rule (approved > most recent > longest). It also discloses the degraded path (compared_wording=false, empty clusters) when the embedder cannot run — an important failure mode not visible in annotations.

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 core action, determinism, and propose-only nature are front-loaded, then the return shape and keeper rule follow. It is dense and leans on payload-field enumeration ('{id, text, state, origin, provenance, usage_count, best_score}') that adds bulk, but nearly every sentence carries operational information.

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?

With no output schema, the description fully documents the cluster return shape, keeper rule, and degraded behavior — an agent can interpret results correctly. The only real gap is how to source entity_id, which is left implicit.

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?

There is one required parameter with 0% schema description coverage, so the description must carry it. It repeatedly frames the scope as 'the entity's active points', which lets an agent infer entity_id identifies the target entity, but it never states the identifier's form or how to obtain it (e.g., via kb_list_entities).

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 resource ('Similar bullets on one Career KB entity, clustered, with a proposed keeper') and immediately names the downstream siblings it feeds into. An agent can distinguish it from kb_combine_points, kb_retire_points, and kb_list_points without opening any schema.

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?

Explicitly frames the tool as propose-only ('nothing is written') and routes the agent onward: kb_combine_points for one claim in other words, kb_retire_points for a similar but stale point. This is a clear when-to-use / what-to-do-next mapping against the alternatives.

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