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

The description frames this purely as a read ("Read saved and pending takes"), while annotations declare readOnlyHint=false and destructiveHint=true. For a read-framed tool, destructiveHint is a serious mismatch an agent cannot reconcile from the text. The description also says nothing about what a destructive read could affect, or about the session prerequisites (catalog version, skill proofs) the required parameters imply.

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?

Three short sentences with the core purpose front-loaded and no filler. The cursor instruction is actionable, though the term "nextCursor" does not appear anywhere in the schema and the final sentence is opaque without surrounding context. Minor terminology drift costs a point rather than a rewrite.

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?

An output schema exists, so return values need not be described, and the high parameter count is largely covered by schema descriptions. What is missing is the behavioral frame: why a read-shaped tool carries destructiveHint=true, and how its cursor relates to the schema's "after" parameter. For a six-parameter, nested, session-enveloped tool, the description is adequate but thin.

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 50%: read_skills, expected_catalog_version and publication_proposal_id are documented in the schema, while media_id, after and limit are not. The description does add pagination meaning ("Follow nextCursor to read older takes"), but it uses the name nextCursor where the schema's parameter is "after," forcing the agent to infer the mapping. Coverage of limit and the read_skills envelope is left entirely to the schema.

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 with scope: "Read saved and pending takes for one media file." That is enough to separate it from sibling mutations such as genads_select_take or genads_recover_take, though those siblings are never named. The closing line gestures at conceptual boundaries ("captured result, a selected take and a reviewed source are separate facts") without tying them to a specific alternative tool.

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 one concrete operating instruction — follow the cursor to read older takes — and implicitly warns against conflating a take with a selected take or a reviewed source. It never says when to reach for this versus genads_inspect_take, genads_select_take, or genads_recover_take, all of which sit adjacent in the sibling list. Usage is therefore implied rather than prescribed.

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