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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds valuable behavioral context: 'read-only and River-root-first with no destructive side effects', 'treats TF-RIVER as the canonical issuer thesis graph and by_issuer as a lookup surface only', and 'Missing nodes are returned in missing_or_unresolved instead of inferred.' These details clarify system behavior and error handling without contradicting 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 description is a single dense paragraph that front-loads the core purpose, then enumerates parameters and behavior efficiently. Every sentence adds distinct value: purpose, parameter list, defaults, behavioral guardrails, and usage timing. No filler or redundancy.

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?

Given the tool's complexity (10 optional parameters, output schema present, many siblings), the description is complete: it covers what the tool does, which parameters to pass, default behavior, key semantic distinctions (canonical vs lookup), error handling for missing nodes, and when to use it relative to article_thesis_map. With an output schema available, the lack of return-value details is acceptable.

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 100%, so the baseline is 3. The description adds meaning by listing which parameters are relevant ('pass current_tripcode, article_tripcode, tripcode, river, river_tripcodes, issuer, or ticker') and clarifying defaults (object_type defaults to TF-SUB, include_unpublished defaults to false, limit defaults to 25). It groups parameters by purpose, helping the agent choose among the many optional fields, but does not deeply explain each parameter beyond the schema.

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 (discover) and resource (TF-SUB article nodes), then specifies three input paths: current article TripCode, issuer TF-RIVER root, or issuer lookup index. It also distinguishes from the sibling tool article_thesis_map by stating 'Use this before article_thesis_map', making its unique role clear.

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?

Explicit guidance is provided: 'Use this before article_thesis_map so subscribers do not need to manually paste old River TripCodes.' This clearly states when to use this tool over an alternative. It also enumerates accepted parameter groups and defaults, giving the agent enough context to decide when this tool is appropriate.

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