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 still adds real behavior context: no invitations are sent as a side effect, email addresses are withheld from the payload, and the returned IDs are meant to be reused as assignees. It does not mention pagination behavior in prose, but the schema covers that.

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 short sentences, front-loaded with the core verb+resource and scope, followed by the practical use and the two negative constraints. Every sentence earns its place with no redundancy.

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?

An output schema exists, so return values need not be re-explained, and the input schema fully documents all three parameters including pagination. The description covers purpose, exclusions, and downstream use, leaving only very minor omissions such as result ordering or page size behavior.

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 100%, and the schema already documents projectId, limit, and the after cursor with format, bounds, and defaults. The description adds nothing parameter-specific beyond the schema, so the baseline 3 applies.

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 ("List existing members of an accessible project") and scopes it to accessible projects, which separates it cleanly from siblings like list_projects and list_project_statuses. It also declares the downstream purpose of the returned IDs, making the tool's role unambiguous.

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 clear usage context ("Use their IDs for task assignees") and two explicit exclusions: it does not invite anyone and does not expose email addresses. It stops short of naming an alternative tool to use for inviting or for fetching contact details, so it is strong but not fully routing.

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