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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description nonetheless adds meaningful context beyond them: no new provider call, no balance charge, no cash reward/GP, and the caveat that source support and reported phone answers still require review and that pending/unknown is not completion.

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 compact sentences with the read action front-loaded, so it is not padded. But the dense, run-on phrasing ('same durable capability task, safe partial answer evidence and actual status') hurts readability without adding proportional value.

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 single-parameter read tool with no output schema, the description covers the return semantics (partial answer evidence, actual status), the cost implications, and the interpretation caveat about pending results. It is nearly complete, with only the task_id semantics left unaddressed.

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?

The single parameter task_id has zero schema description coverage, so the description carries the full burden of explaining it — yet it never mentions task_id, its format, or where to obtain it. With 1 param at 0% coverage, this is a clear gap rather than an acceptable baseline.

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 verb 'Read' and resource 'capability task' give a workable sense of what this does, and it is distinguishable from the sibling evuun_run_capability. However, phrases like 'this application's same durable capability task' and 'safe partial answer evidence' are grammatically awkward and obscure exactly what is retrieved. The core purpose lands but only after parsing.

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 implies a status-check use case by stating 'No new provider call, balance charge,' which hints at when to use this instead of re-running. But it never explicitly names evuun_run_capability as the alternative or states the condition (e.g. poll an existing task rather than start one). Usage is inferred rather than stated.

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