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

Adds substantial context beyond the annotations: all inputs are validated before any fetch happens, results are returned per item with individual errors, processing is sequential, and the credit model charges one credit only for a fresh live success while demos, cache hits, and failures are free. That is exactly the kind of cost/failure semantics an agent needs before committing to a call, none of which the readOnlyHint/openWorldHint flags convey.

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?

Four tight sentences with no filler, but the ordering is slightly off: it opens with the validation precondition rather than the core action, and the reader must infer the operation from 'fetching.' Still, each sentence carries distinct, non-redundant information.

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 covers the shape of the response at a high level ('per-item successes/errors') and covers the cost and ordering semantics, which is enough to call it correctly. It leaves the exact error object shape and whether partial successes still cost credits fully explicit only for the live-success case.

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 baseline is 3, but the description adds real meaning by tying the mode and freshness fields to billing: a 'live' fresh item costs a credit, demo and cache hits are free. 'Processed sequentially' combined with max ten also clarifies that per-item errors do not abort the run, which the schema alone does not express.

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 title plus phrases like 'before fetching any' and 'per-item successes/errors' make clear this is a batched profile fetch of up to ten items. It is distinguishable from the singular sibling via the ten-item cap and per-item results, though the description itself never plainly states 'looks up public profiles' — that verb+resource lives in the title rather than the description body.

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?

Batch usage is implied by 'Maximum ten items' and the per-item cost model, and the zero-cost demo path nudges toward non-live usage. However, there is no explicit 'use this instead of signalshelf_profile when you have multiple handles' guidance, and no stated prerequisite (e.g., credits or auth) for choosing it over the single-profile sibling.

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