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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses pagination (next_offset until null), coverage semantics (incomplete coverage explicit, aggregate evidence not first-cell), re-test state semantics (only queued/running are still_measuring; shipping alone is unmeasured; re-tests estimated and confirmed in the app), and credit accounting. That is substantial behavioral context, though it is stated as bare assertions rather than organized guidance.

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 the verb and resource, and every clause carries domain meaning, but it is one long run-on paragraph of stacked particulars and jargon (Wilson 95% range, still_measuring, credited accounting) with no grouping, which hurts scanability.

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 carries the full return-shape burden and does so in detail (rendered titles/descriptions, loss rationale, pick rate and Wilson range, re-test status, Outcomes), plus pagination and required scopes. It is close to complete for this complex read tool, though the offset/next_offset relationship and the single-action mode could be stated more cleanly.

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%: actionId is documented ('Read one Action and its re-test result'), while offset is undocumented in the schema. The description partially compensates by describing the pagination contract ('Follow next_offset until null'), giving offset usable meaning, but it is borderline rather than a full coverage of both parameters.

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 (Read) and resource (100 Agent Picks Actions) with a clear scope, and the dense field list (titles, descriptions, loss rationale, pick rate, re-test status, Outcomes) makes it distinguishable from siblings like get_agent_picks_cells or get_agent_picks_summary. It is clear what the tool returns, though it never explicitly contrasts itself with those siblings.

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?

'Follow next_offset until null' gives pagination guidance, and 'Requires Agent Picks and visibility.read' states a prerequisite. However there is no when-to-use vs when-not, and no routing to the alternative Agent Picks tools an agent would weigh against this one.

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