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

With no annotations, the description carries the behavioral burden and does so meaningfully: it discloses that pipeline artifacts are counted but not listed, that only names and metadata (not contents) are returned, and that nextbid_documents text is fetched via read_file. These scoping constraints are real behavioral context. It omits anything about auth, pagination, or size limits.

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?

It is a single front-loaded sentence, but it is packed with nested parentheticals that make it harder to parse quickly. The return-structure detail earns its place, yet the phrasing could be tightened into a cleaner list of what is included versus excluded.

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 output schema and no annotations, the description does the work of describing the return shape (two document groups, their fields, what is excluded). An agent knows what it will receive and how to act on it. The main missing piece is guidance on the nb_id value itself.

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% for the single nb_id parameter, so the description must compensate. It does add that the id scopes to 'one opportunity', but it never explains the id's shape, source, or how to obtain it (the ^NB\d{8}$ pattern lives only in the schema). Partially compensating, not fully.

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 names the resource (the document set for one opportunity) and enumerates exactly what is returned: source_documents with their metadata fields and nextbid_documents. It implicitly distinguishes itself from reading tools by noting content is readable via read_file and that this returns 'names and metadata only'. It is clear, though no explicit verb like 'list' anchors the opening.

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?

Usage is implied by the framing: use this to see what documents exist for an opportunity, then read_file for the normalized text. It routes to one sibling (read_file), but gives no explicit when-to-use/when-not guidance and does not differentiate from get_document_text or list_files, which could easily be confused with it.

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