get_capture

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds substantive behavior beyond that: it discloses that superseded history is included alongside live values, that each field carries provenance and confidence, and critically that this tool never serves bytes and the original must be fetched via the documents endpoint. That last point is a non-obvious behavioral constraint an agent would otherwise get wrong.

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 dense sentence with the most important information (what you get back) front-loaded, and no filler. The nested parentheticals and internal codes ('A31', 'E00 document reference') make it harder to parse than necessary, but every clause carries content.

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, the description sensibly takes on the burden of describing the return shape, and does so in reasonable detail including the QR-evidence and history aspects. However, it leaves both required identifier parameters entirely unexplained and uses unexplained domain codes (A31, E00), so an agent knows what it gets back but not how to construct the call.

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 neither of the two required parameters (captureId, workspaceId) is mentioned anywhere in the description. The description does not say what a capture ID looks like, whether the workspace ID scopes lookup, or how the two interact. With zero schema coverage, the description needed to carry this and does not.

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 precisely what is returned: a single capture with all fields, live plus superseded history with provenance/confidence, associated qrPayloads, and the document reference. This is far more specific than the bare name and implicitly distinguishes it from the sibling list_captures ('one capture' vs a list). It never uses an explicit retrieval verb, and the sibling names docs_get_content/files_get_content are garbled ('documents_get_content'), but the resource and scope are 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 one real piece of routing guidance: 'the E00 document reference to fetch the original via documents_get_content. A31 never serves bytes itself' tells the agent not to expect binary content here and where to go instead. Beyond that, there is no statement of when to call this versus list_captures, get_document, or get_entry, and no prerequisites are given.

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