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

Adds substantial context beyond the annotations: same-organization scoping, the polling cadence for running states, the authorization scope (agent:read), and an explicit list of content the response excludes (buyer text, deliverables, evidence quotes, execution details). None of this is derivable from the readOnly/idempotent hints.

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 dense sentences with zero filler: purpose first, then the polling rule, then the data-boundary/auth caveat. Everything an agent needs up front.

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 no output schema, the description does well to disclose what the response excludes and that a pollAfterSeconds field drives polling. It stops short of describing the status values themselves or the other returned fields, which is the main remaining gap for a polling-status tool.

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 runId parameter has 0% schema description coverage, so the description must carry the meaning. It implies runId identifies a run within the same organization (an access constraint), but never explains the identifier's origin or where to obtain it, leaving a gap for a UUID-typed required param.

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 and resource: reading same-organization saved delivery status for a run. It's clear what the tool delivers versus a content-retrieval tool, though it doesn't name the sibling (procurement_artifact__get) that returns the excluded artifacts.

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 concrete operational guidance: if status is running, wait pollAfterSeconds before re-reading, which describes the intended polling loop. It does not explicitly name an alternative tool for fetching deliverables, leaving that routing implicit.

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