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

Annotations already disclose the safety profile (not read-only, not destructive, not idempotent, closed-world), so the description only needs to add context. It contributes the 'scientist-reviewed' curation concept and the upsert semantics, but omits what happens on duplicate adds, permission requirements, or whether existing note/relevance values are overwritten.

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?

A single front-loaded sentence with no filler. It is efficient, though arguably under-specified rather than deliberately concise.

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 mutation tool with four undocumented parameters, no output schema, and no parameter coverage, the description leaves the agent without enough to call it correctly (e.g. valid relevance values, update-vs-insert behavior). It should carry more of that burden.

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% and none of the four parameters are explained in the description. 'Relevance' defaults to 'unreviewed' with no enum, so the accepted values are entirely undocumented; the description only implicitly names the collection and retrieval concepts.

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 clear verb ('add or update') and resource ('a retrieval in a scientist-reviewed evidence collection'), which is enough to tell it apart from create_evidence_collection or list_evidence_collections. It doesn't explicitly name sibling tools, but the action is unambiguous.

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?

There is no guidance on when to use this tool versus create_evidence_collection, link_claim_evidence, or search_evidence. The 'add or update' phrasing hints at upsert behavior but never states the condition that selects this tool or the prerequisites (e.g. must the collection already exist?).

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