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

Annotations already provide readOnlyHint=true and destructiveHint=false. The description adds pagination guidance ('Use small page sizes (25-50) with sequential calls') and default sort, which is beyond annotations. However, this guidance directly contradicts the input schema's size description ('Raise it to pull the full set in one call'), making the behavior advice misleading rather than transparent. It also omits any mention of date range handling or output format. Given the contradictory advice, the disclosure is poor.

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?

The description is concise and well-structured, with a clear purpose sentence followed by terse labeled sections (STATUS VALUES, SORT OPTIONS, PAGINATION). It front-loads the main action. However, the inclusion of the contradictory pagination guidance is a substantive error, though it does not affect the structure's efficiency.

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?

The tool has 7 parameters and no output schema, with annotations covering safety. The description covers status, sort, and pagination, but not date range parameters or return values. More critically, the pagination advice conflicts with the schema, leaving an agent uncertain whether to use small pages or raise size. This is a significant gap in actionable completeness.

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 all parameters have descriptions. The description repeats enum values and sort options already in the schema. Its only unique parameter advice – pagination – conflicts with the schema's own described behavior (schema suggests raising size for one call, description advises small pages and sequential calls). This contradictory guidance undermines rather than adds semantic value.

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 description clearly states the tool's function: retrieve opportunities for given domains with status filtering and pagination. The verb 'Get' and resource 'opportunities' are specific, and it mentions filtering and pagination capabilities. While it does not explicitly contrast itself with siblings like get_account_summary_insights, the 'opportunities' scope is distinct enough. No tautology.

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?

The description gives operational details (status values, sort options, pagination strategy) but does not state when to choose this tool over alternatives like get_account_summary_insights or get_insights_report. Usage is implied by the resource name, but there are no explicit exclusions or alternative routing. So it's adequate but not explicit.

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