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

Annotations already establish readOnly/idempotent/non-destructive/non-open-world, and the description adds genuine operational context beyond that: the native CLI/SDK validates digest, size and media type without redirects or executing files, remote MCP does not write local files or return binary contents, and missing capture/durability must not be inferred. This is substantive disclosure that the annotations alone do not provide; it is dense and slightly cryptic but earns its place.

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?

The lead sentence is front-loaded and identifies the resource plus its two download affordances. The remainder is a run-on of dense clauses with terse jargon ('same-scope local CLI download template', 'exact API references') that is harder to parse than it needs to be, though most sentences carry distinct facts.

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 read-only listing tool with no output schema, the description covers the return surface reasonably (scoped API download paths, CLI template, large manifests retaining API references, no binary contents). The significant hole is the complete absence of parameter meaning for a three-identifier tool, which an agent needs in order to invoke it correctly.

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 description coverage is 0% for all three required parameters (projectId, environmentId, runId), and the description never explains any of them beyond the phrase 'for one run'. With three undocumented identifiers and no enums, the description fails to compensate for the schema gap, leaving relationship between project/environment/run ambiguous.

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 a specific verb (List) and resource (actual retained files/documents for one run), which is unambiguous and unique among the sibling tools. It stops short of naming any sibling to distinguish against, but the resource is distinctive enough that an agent can match it without opening a schema.

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 real when-not guidance ('Pending uploads are not available evidence', 'Never rerun a target to retrieve evidence', 'API-only runs need not have screenshots'), which steers behavior. However, it never names an alternative tool or states the precondition for choosing this over, say, firedrill_retention or firedrill_report, so usage is only implied.

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