get_codelist_submission_values

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

The annotations only declare readOnlyHint=true, so the description carries most of the behavioral burden and does so: payload-based resolution, a termsResolvedByDetailRequest count reporting fallback terms, total/hasMore paging signals, a 2000-per-page clamp (limitRequested echo), and a concrete scale note that LBTESTCD's 2397 terms need two pages. It doesn't discuss auth or failure modes for an invalid codelist ID, which keeps it off a 5.

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 key point — don't call get_term per term — is front-loaded before mechanics and the example, and every line carries operational content (cost comparison, projection, paging, ID pitfalls). It is dense and runs long, with the closing 'use get_term for single-term detail' partially restating an earlier line, so it falls short of a 5.

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?

For a six-parameter read tool with no output schema, the description supplies the return shape (three columns plus an example row), page-size and total/hasMore semantics, and the fallback-count field, which is everything an agent needs to call it and interpret the result. The scale warning about two-page codelists closes the remaining gap.

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 already 100%, so the baseline would be 3, but the description adds real semantic guidance on top: fields can be narrowed to 'name,submissionValue' (or extended with definition/synonyms), pagination is driven by total/hasMore rather than blind looping, and the codelist ID has documented traps (C667 does not exist; C141657 is not LBTESTCD).

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 states a precise verb and resource (paginated retrieval of a codelist's terms and their submissionValue) and fixes the output shape as three columns (code / name / submissionValue). It explicitly sets itself apart from the sibling get_term and shows a concrete example (package='sdtmct-2024-03-29', codelist='C66731' → [{code: C16576, ...}]).

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 says when NOT to use the per-term path: reading the package payload covers the whole table in 1–2 calls versus roughly 150s / 260 calls to get_term, with a fallback to per-term detail only for terms missing from the payload. It also routes to get_ct_packages when the package is unknown and to get_variable / get_codelists when the codelist ID is uncertain, and reserves get_term for full single-term detail.

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