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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered; the description's "(read-only)" merely echoes that. The value-add is disclosing the return shape ("Each item includes analysisId and revisions"), which matters because there is no output schema, though pagination, result caps, and behavior when the period is omitted are unstated.

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, front-loaded with what the tool returns, then the required inputs, then the downstream use. No filler and nothing repeated from the schema verbatim.

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 six-parameter read tool with no output schema, it covers the essentials: required ids, the two period formats, and the key fields of each returned item. Remaining gaps are modest but real — no indication of result volume, ordering, or whether a missing period is rejected client-side or by the server.

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 the baseline is 3, but the description adds real meaning by framing startDate/endDate and qStartMs/qEndMs as mutually exclusive period-specification routes. This compensates for the vague qStartMs/qEndMs schema text ("Optional integer (0 = omit / server default)") by telling the agent they are an epoch-millisecond alternative to the date pair.

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 ("List saved analysis items") plus the scoping axes (view and period), which is exactly what distinguishes it from report_analysis_create/update/run in the sibling set. The parenthetical "(read-only)" and the pointer to report_analysis_update further pin down its role.

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 concrete preconditions (clientId, viewId, and either startDate+endDate or qStartMs+qEndMs) so an agent knows what must be assembled before calling. It also implies a workflow by noting the items carry revisions "for report_analysis_update," but it never explicitly states when to prefer this over alternatives like report_analysis_run or report_card_get.

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