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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description's one contribution is disclosing the shape of the result (name, size, type, who added it), which is genuinely useful given there is no output schema. It says nothing about ordering, pagination, or whether an assignment with no files returns an empty list or an error.

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?

Very short and the scoping constraint ('one assignment') comes first, which is good front-loading. However, the fragment form with a colon-list reads as a field inventory rather than a statement of what the tool does, so brevity comes at the cost of a clear leading action.

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?

This is a simple read-only list tool, so expectations are modest, but with no output schema and 0% parameter documentation the description should explain project_id and the return shape more fully. As written, an agent can guess the call but cannot confidently construct it or interpret an empty result.

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 two required parameters, so the description carries the full burden and largely fails. 'One assignment' loosely maps to assignment_id, but project_id is never mentioned, leaving the agent to guess why both identifiers are required or whether they must be consistent.

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 identifies the resource (files attached to one assignment) and enumerates the returned fields (name, size, type, who added it), which is more than the bare title. But it is a noun fragment with no verb, so the agent must infer 'list' from the tool name. It does implicitly contrast with erp_attach_document, but never states the distinction.

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?

There is no when-to-use guidance at all: nothing tells the agent to call this rather than erp_get_assignment (which may already include attachment metadata) or erp_attach_document for the write direction. The phrase 'one assignment' hints at scoping but is not framed as guidance.

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