propose_definition

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

With no annotations, the description carries the full burden, and it is mostly strong: it discloses that candidates are grounded in computable data, include explanations/coverage, and must not be selected silently. It doesn't explicitly state that nothing is saved yet, though 'ready-to-save' and 'present to the user' strongly imply it.

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 front-loaded with the usage trigger and is only three sentences. The first sentence is long and list-heavy, but every part adds useful 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?

It covers the main workflow and output well, and an output schema exists, but it omits the optional parameters and does not clarify follow-up tool calls such as save_definition after user approval. This is acceptable for a tool with only one required parameter but not fully complete.

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 the description should compensate by explaining the parameters. It only implicitly covers term; entity and context are completely unexplained, leaving the agent to guess whether or when to populate them.

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 an explicit trigger: call when a concept lacks a definition or when query returns unresolved_term. It also names the concrete outputs (near-matches, candidate definitions, coverage, related attributes) and makes the tool's role clear relative to plain query or lookup tools.

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?

It tells exactly when to call the tool and instructs the agent to present candidates to the user rather than choosing silently. It does not explicitly name alternatives like get_definition or save_definition, but the no-definition/unresolved-term condition implicitly separates it from those.

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