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

Annotations only declare readOnlyHint, so the description carries the rest — and it does: images return as viewable content, other types return metadata plus a time-limited download URL, and URLs change on every call while resourceId is the stable identity. The anti-retry instruction is exactly the kind of behavioral detail annotations cannot express and prevents a common agent failure loop.

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?

Front-loaded with purpose, then return-shape behavior, then the retry caveat — a sensible escalation. It is denser and longer than a two-sentence ideal, but no sentence is redundant or repeats structured fields.

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 two-parameter read tool with no output schema, the description covers what comes back in each case, how to pass the URL along, and the retry pitfall. Nothing an agent needs in order to call it correctly and interpret the result is missing.

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 100%, so the baseline is 3; the description adds genuine meaning by framing resourceId as a stable identity sourced from answer resources. productId is left entirely to the schema, which is acceptable given its own description points at listProducts.

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?

States a specific verb and resource ("Fetch one file uploaded by a tester as a step answer") and pins provenance by saying the resourceId comes from getTaskResults or getStepResults. It does not explicitly differentiate itself from attachment/media siblings such as getTicketAttachment, getStepMedia or getTaskMedia, so the distinction has to be inferred from the 'step answer' wording.

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?

Gives explicit when-to-use guidance (share the URL with the user, or fetch it yourself when the user asks you to read or analyze the file) and an explicit when-not case: a metadata-plus-URL result is the intended answer, not an error, and must not be retried. It also points to the upstream tools that produce a valid resourceId, leaving no routing ambiguity for the common case.

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