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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description goes further by disclosing polling behavior, the concise-vs-full detail modes, the fields of each finding, and the meaning of hidden and reportUrl — genuine behavioral context beyond the annotations.

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?

Four tightly packed sentences, front-loaded with purpose then usage then parameter semantics then output hints. No filler, and the most decision-relevant information (what it is, when to call it) comes first.

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 two-parameter read tool with an output schema, this is complete: it covers purpose, polling loop, parameter modes, and finding shape. Nothing an agent needs in order to call 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 only 50% (detail has no schema description), but the description compensates by explaining 'concise' as counts plus the first 25 findings and 'full' as everything, including the default. That adds real meaning beyond the enum alone, though scanId gets no elaboration beyond its schema description.

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 opens with a specific verb+resource ('Read the progress and findings of a scan') and ties the scan back to its producers, proofread_url or proofread_site. An agent can immediately distinguish this polling/read tool from the two sibling proofread tools.

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?

It gives an explicit invocation cadence ('every 10 seconds') and termination condition ('stop when done is true (status is not processing)'), plus the required key (scanId). This is exactly the operational guidance needed and there is nothing left to infer.

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