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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds real value by disclosing that the response includes vendor pagination metadata and represents a single page rather than the full set. It stops short of stating rate limits or default page size behavior, but the pagination caveat is the key non-obvious trait.

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, waste-free sentences. The field inventory comes first, then the endpoint, then the pagination caveat — reasonably front-loaded, though leading with an action verb would have been sharper.

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 13 parameters and no output schema, the description should say more about what is returned and how filters combine. It correctly warns about single-page results, which is the most important gap-filler, but leaves the '_q' free-text parameter and the response shape unexplained.

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 77% and documents page, limit, sort, direction, tags, status, and dates. The description echoes some of those concepts (status, due dates, tags) but adds no syntax or semantics beyond the schema, so the baseline of 3 is appropriate rather than a lower score.

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 names the resource ('Maintenance tasks') and its fields plus the underlying endpoint GET /v2/tasks, so an agent can infer this is a read/list operation. However, it never states the verb 'list' explicitly and doesn't distinguish itself from arthur_get_task or arthur_list_workorders, so the boundary relies on the tool name alone.

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 only usage-relevant hint is 'this is one page, not the whole portfolio', which tells the agent to paginate but not when to pick this tool over arthur_get_task or arthur_list_workorders. There are no exclusions, prerequisites, or conditions for choosing alternatives.

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