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

Annotations only declare readOnlyHint, openWorldHint, and idempotentHint. The description adds substantial behavioral context: default paging behavior (first 50, workCount total, nextOffset), how limit and offset interact, the option to slim payloads, chaining readiness of external IDs to Crossref/PubMed/arXiv, and the caveat that works are self-reported and may be incomplete. This goes far beyond the safety hints.

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 about four sentences, front-loaded with the core purpose and immediately followed by return details, paging, chaining, and a data-quality caveat. Every sentence adds distinct value; there is no fluff, redundancy, or irrelevant detail. The structure guides the agent from what it does to how to page and what to expect.

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 output schema and annotations are present, the description covers everything an agent needs to call correctly: what fields are returned, how to page with offset/limit/nextOffset, how to get full details via orcid_get_work_detail, how to chain external IDs, and the self-reporting limitation. No missing operational or safety details were identified.

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 each parameter is fully documented in the schema. The description adds value by clarifying the paging interaction ('the full list is sliced locally'), the default and max for limit, the purpose of include_external_ids as a payload optimization, and the two accepted formats for orcid_id. This is more than a mere restatement, justifying an elevated score above the baseline.

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-resource pair, 'Retrieve works associated with an ORCID iD,' and enumerates content types (publications, datasets, software, preprints) along with returned fields (put-codes, titles, types, dates, journal names, external IDs). It clearly distinguishes from siblings like orcid_get_work_detail (by referencing it for full records) and other resource-specific tools (affiliations, funding, etc.) through the focus on works.

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 provides clear usage context: it explains default limit of 50, paging with offset and nextOffset, the option to reduce payload with include_external_ids, and explicitly routes to orcid_get_work_detail when full records including abstracts are needed. It lacks an explicit 'do not use when' statement, but the alternative path is explicit enough that an agent can choose correctly.

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