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

The description does add real behavioral context: it discloses an access side effect (the first open is recorded and visible to the person's insurance agents) and asserts the file itself is unchanged. However, that assertion directly conflicts with the annotation destructiveHint=true and with readOnlyHint=false, which signals a state-changing operation; the description never explains what the 'destructive' aspect actually is (e.g., whether recording the open is irreversible or whether some derived data is rewritten). The mismatch leaves the agent with a misleading safety picture.

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?

The core return value is front-loaded in the first sentence, but that sentence is a long compound construction with stacked parentheticals ('the text PolicyVera reads out of a PDF and, when it fits, the file itself as a resource for apps that show files') that is hard to parse. The final sentence about agent filing copies reads as a leftover caveat rather than an integrated rule.

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 does the necessary work of explaining what comes back (extracted text, and the file itself as a resource when it fits) and warns of the open-tracking side effect. What remains missing is failure behavior — what an agent sees for an unknown, expired, or unauthorized documentId — but for a one-parameter fetch tool the coverage is largely adequate.

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 100% and the single documentId parameter already carries format, pattern, and provenance ('from my_documents') in the schema. The description restates the same provenance without adding format, error, or lookup semantics, so it meets the baseline rather than exceeding it.

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 uses a specific verb and resource ('Returns one of the person's own files on PolicyVera') and enumerates what the file can be (declarations page, ID card, binder, other upload), plus what is returned (extracted text plus the file as a resource). It never explicitly contrasts itself with similarly named siblings such as read_policy_document or get_quote_document, so an agent must infer the boundary from the 'person's own files' scoping.

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 gives one useful precondition — 'documentId comes from my_documents' — which tells the agent to obtain the id from another tool first. The closing exclusion ('An insurance agent's own filing copy is not among them') narrows scope but is about agent-authored copies, not about when to pick this tool over read_policy_document; there is no explicit when-to-use/when-not guidance versus alternatives.

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