Get filing suggestions

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

Annotations already declare readOnly, idempotent, non-destructive. Description adds useful behavior beyond them: the result is model-dependent and not authoritative, so it must be verified. This is honest about output variability and aligns with the annotations.

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?

Two sentences deliver the content, purpose, and an important caveat with no filler. The substantive detail comes first and the verification warning follows naturally.

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 low-complexity read-only tool with one param and strong annotations, the description is largely complete: it names the output categories and reliability caveat. It does not describe the exact response structure, but no output schema exists and the listed suggestion types give enough orientation for selection and invocation.

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?

There is one id parameter with zero schema description coverage. Description references 'a document' but never explicitly states that id is the document identifier or how invalid ids behave. The id is simple and self-evident, but the description does not truly compensate for the missing schema property text.

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 identifies a specific verb-resource relationship: it returns Paperless' classifier suggestions for a document, enumerating the fields (correspondents, tags, document types, dates). It is clear, but does not explicitly name the nearby sibling get_document_ai_suggestions, relying on the phrase 'Paperless' own' to imply the distinction.

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 states clear use context: useful as a starting point when triaging. It also tells agent to verify before applying because suggestions depend on model quality. It does not name alternative tools/exclusion conditions, so it misses the full 5.

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