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

With annotations supplying readOnlyHint=false, destructiveHint=false and idempotentHint=false, the description still adds real context: the link is a credential that signs a browser into the person's account, PolicyVera only issues it for that person, and it expires ('lives for the minutes given'). The expiry detail is muddied, though, because no lifetime parameter exists in the schema, so 'the minutes given' points at configuration the agent cannot see.

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 effect is front-loaded, but the long parenthetical catalogue of pages duplicates the enum in the schema and inflates the first sentence considerably. The sentence 'The link signs a browser in to the person's account, and PolicyVera makes one only for the person' is also partly repetitive of the opening clause.

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?

There is no output schema, and the description only partially covers the return: it names whatTheyGet but never says the reply carries the URL itself or when the link stops working, beyond the vague 'minutes given'. For a token-issuing tool whose output is a credential, that leaves the agent guessing about the response shape and lifetime semantics.

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%, so the baseline is 3. The description restates the destination choices that the enum already enumerates and adds little new about requestId, documentId, download or sideBySide beyond the schema's own descriptions, which are more precise (including the check_quotes lookup hints).

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 outcome: it "returns a link that signs the person in on their own browser and opens one of their pages," and it enumerates the destination pages. That is much clearer than a bare 'get link', but it never names the sibling link tools (get_review_link, get_upload_link) to sharpen the boundary, so an agent must infer the distinction from the page list alone.

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 rather than stated: the value proposition (a person opens their own page already signed in) suggests when to reach for it, but there is no explicit 'use this when a human needs to view X' and no 'do not use this when you only need the data — use read_messages/my_policies instead'. Given the sibling tools overlap heavily with the listed destinations, an explicit exclusion would have been valuable.

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