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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds a genuinely useful behavioral detail beyond the annotations — that each entry includes expiration and open counts — but says nothing about pagination, ordering, or what happens when a run has no links.

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?

One compact sentence that front-loads the resource and then the returned fields; nothing is redundant. It is slightly under-specified rather than padded, so it loses a point for lack of any routing or scoping clause rather than for verbosity.

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 simple read-only single-parameter list tool, the description covers what is returned (links plus expiry and open counts), and annotations cover safety and openness. Absent an output schema, the brief field listing is reasonable; only edge-case behavior (empty results, pagination) 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?

There is only one parameter and schema coverage is 100%, so the schema fully documents runId. The description's 'for a run' reinforces that runId is a filter rather than an identifier of a single link, which is a small amount of added meaning; baseline for a fully-covered single param is 4.

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 names the resource (share links) and the scoping key (a run), and implies a read/list operation through 'made for a run, with when they expire'. It is clearly distinguishable from the create_share_link/delete_share_link mutations, though it never says 'list' explicitly and relies on the name/title for the verb.

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 only implied by the noun phrase: you'd call this to inspect existing links for a run. There is no explicit when-to-use statement, no note on what to call instead when you want to create or revoke a link, and no prerequisites mentioned.

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