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

No annotations are provided, so the description carries the full burden, and it does disclose the safety profile ('Read-only') plus the return contents including autocorrect state — useful context an agent would not otherwise have. It stops short of ordering, pagination over results, or behavior when search_id is unknown, which for a read tool is a moderate rather than severe gap.

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?

Two short clauses, front-loaded with the safety signal, with the field list packed efficiently into one parenthetical. No filler, though the sentence is a fragment that omits a subject-verb frame that would make the read action explicit.

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 field enumeration earns its place and tells the agent what to expect back. However, with no annotations and 0% schema coverage on a required search_id plus a capped limit, the definition leaves the agent guessing about scoping and pagination behavior.

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 description coverage is 0% for both parameters, so the description must compensate but does not: neither the required search_id scope nor the meaning/range of limit (1-100, result cap) is explained. The parenthetical enumerates returned data, not input semantics.

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 resource and scope: past ICP-QA runs, plus a parenthetical enumeration of the fields returned (checked, fits, uncertain, unfit, quality %, keyword changes). It is clear this is a history read, not a run trigger, though it never names the sibling (sdr_icp_qa_run) that performs the actual check.

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?

'Read-only' and 'Past ... runs' imply this is a retrieval call, but there is no explicit when-to-use, no mention of what to use instead for a new run (sdr_icp_qa_run) or for review state (sdr_icp_review), and no prerequisites stated for search_id.

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