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

No annotations are supplied, so the description carries the full disclosure burden. It usefully reveals the default vs expanded result set and the internal version/class semantics, but says nothing about permissions, result size, ordering, or whether the listing is paginated.

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?

Three dense sentences, front-loaded with what is returned, then the include semantics, then the retrieval alternative. Some parenthetical jargon makes it terse, but no sentence is wasted.

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?

With no annotations and no output schema, the description does the heavy lifting reasonably well: it names the returned content classes, explains how include expands the set, and routes to read_file for content. It stops short of describing the response shape or pagination, but covers what an agent needs to choose and call the tool.

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 must compensate. It explains include='all' well (adds artifacts and superseded generations), but nb_id is only implied by 'one opportunity' and its NB\d{8} pattern is never clarified in the description.

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 what is listed and for what scope: 'the current stored documents for one opportunity', with the concrete content classes ('Document 0 markdown/json and normalized attachment markdown'). It clearly distinguishes itself from read_file ('Use read_file to fetch one'), but does not differentiate itself from the sibling list_documents, leaving some ambiguity between the two listing 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 explains the mode switch ('include="all" adds pipeline artifacts ... and superseded Document 0 generations') and names the alternative for retrieval ('Use read_file to fetch one'). It gives clear context for use but offers no explicit guidance on when to prefer this over the sibling list_documents.

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