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

Annotations already cover the safety profile (readOnly, non-destructive, not open-world), so the description's added value is the key behavioral fact that it returns a URL the user must click rather than acting itself. It does not cover error cases or link expiry, keeping it from a 5.

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 outcome front-loaded and the constraint ('you can't open their browser yourself') positioned before the argument details. Slightly long but every clause carries meaning.

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 correctly states what is returned (a link) and the two required inputs, which is enough for an agent to call and use the result. Remaining gaps (link format, validity) are minor.

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 coverage is only 33%, so the description must compensate, and it does for the ambiguous case: it explains that record_id is the record's id and that id_column can name 'another unique column' to identify the record. The 'table' parameter remains self-evident only by name.

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 a specific verb and resource ('Get a link that opens one record... on its own screen in the Fieldproxy web app') and makes the read-only artifact nature explicit, distinguishing it from record-fetching siblings like get_call or find_customers.

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 clear context for when this is the right call: the agent can't open a browser, so it must hand the user a clickable link. It does not name an explicit alternative or exclusion, but the use case is unambiguous.

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