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

Annotations already establish readOnlyHint=true, and the description adds real value beyond that: required scope projects.read, page 0-based indexing, and the non-obvious vendor quirk that last_modified_since silently defaults to one year ago and older dates are rejected. It stops short of describing ordering or how paging terminates.

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 short front-loaded sentences, each carrying distinct information (scope, paging, history limitation, return contents). Minor terseness issues ('max100', 'Response includes customer names available on projects') slightly reduce legibility.

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?

It covers the hidden truncation behavior that an agent would otherwise get wrong, but with 5 parameters at 20% schema coverage and no output schema, two filtering parameters and the response shape remain undocumented. Adequate, not complete.

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 20% (only last_modified_since is described), and the description supplements page origin and the 100 limit ceiling plus the last-modified default. However opportunity_id and project_status remain completely unexplained in both places, leaving a meaningful gap.

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+resource (read/list projects) and the auth scope required (projects.read). It doesn't explicitly contrast with the sibling builderprime_get_project, but the plural 'projects' plus paging makes the list-vs-single distinction inferable.

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?

The warning that this 'is not a complete all-history report' implies when the tool is insufficient, which is useful, but no positive when-to-use guidance or explicit alternative (builderprime_get_project) is named.

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