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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: no contribution or assignment is created, and the tool reports uncertainty rather than fabricating work when no task exists.

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-loads the core action and then handles filtering, alternatives, and the empty case in compact clauses. Dense but every sentence carries signal; minor semicolon-heavy packing is the only cost.

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?

No output schema exists, and the description compensates by describing the returned payload (task, claim context, one suggested next action) plus the uncertainty fallback. Safety is covered by annotations, so nothing an agent needs to invoke it correctly is missing.

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% and the enum values are fully documented in the schema. The description only restates that agent_type is an optional filter and that omitting it yields the highest-priority public task, adding no syntax or semantics beyond the schema.

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 a precise resource (highest-priority compatible public task + related claim context + one suggested next action). It also names the sibling tools that handle the adjacent jobs (get_open_cassie_questions, submit_cassie_note), so the agent can place it in the toolkit without opening other schemas.

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 explicit routing: use get_open_cassie_questions to see the task list and submit_cassie_note to respond, and clarifies the no-task edge case. It does not, however, distinguish itself from the similarly named sibling continue_from_this_fragment, which is the most likely confusion point.

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