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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, yet the description adds genuinely new context: 'Public; no authentication required', the exact priority-point formula, the USDC nominal conversion, and the fact that refunded/disputed support does not contribute. It also clarifies that sponsorship affects review priority but does not guarantee implementation, which is behavior an agent cannot read from the annotations.

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 text is dense but the first sentence is a policy caveat rather than the tool's function, so the most important information is not front-loaded. Several sentences (USDC parity, refunded support, operator considerations) explain ranking policy that is tangential to invoking the tool.

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 described, and the description covers auth, pagination and filtering adequately for a 7-parameter list tool. The remaining gap is sort/limit semantics, which are neither in the schema descriptions nor the prose.

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%, so the description carries extra weight, and it names four filterable dimensions (category, status, author, text) plus cursor/limit handling. It never explains the sort enum values (priority/newest/votes/funding) or the default limit of 25, leaving several parameters undocumented in both schema and prose.

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 title says 'Find feature and infrastructure requests' and the description implies listing via 'Filter by category, status, author or text', but the body never states the core action plainly or distinguishes it from the sibling get_developer_request. The opening sentence 'Free requests remain visible' is a constraint, not a purpose statement, so an agent must infer the verb+resource from the title.

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?

'Follow next_cursor with unchanged filters' gives real pagination guidance, and the priority formula implies the default sort behavior. However, there is nothing about when to use this versus get_developer_request or create_developer_request, and no stated exclusions.

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