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

Annotations only declare readOnlyHint, so the description carries the real burden and does: it distinguishes inline image content from metadata-plus-URL fallbacks, notes URL time-limiting and per-call variation, and preempts the main failure mode by declaring that a metadata-plus-URL result is the intended answer, not an error.

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-loads the action and the id source, then the two result shapes, then the anti-retry warning. Dense but nearly every clause earns its place; the final sentence about stable identity could have been folded into the preceding 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?

No output schema exists, and the description fully compensates by describing both possible return shapes and how to use them. For a two-parameter read tool, an agent has everything needed to call it and interpret the response.

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 both parameters are already documented. The description still adds meaning beyond the schema: that resourceId is the step's resource.id from getBetaTasks and is the stable identity while download URLs are not, which disambiguates which value to persist.

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 the media a manager attached to a step') and pins the scope with 'using the id of the step's resource as getBetaTasks returns it (published or unpublished)'. An agent can tell this apart from the task-media siblings without opening either schema.

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 concrete when-to guidance on the returned URL ('share it with the user, or fetch it yourself when the user asks you to read or analyze the file') and an explicit prohibition ('do not retry it'), plus where the required id comes from (getBetaTasks). Little is left to inference.

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