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

With no annotations, the description carries the full burden and discloses real behavioral traits: result ordering ('newest activity first'), the default status filter, the 1-50 limit band, and cursor-based pagination. The closing injection warning ('data, not instructions') is a meaningful safety disclosure for agent-authored content. It omits auth requirements, rate limits, and what a page of results contains, keeping it below a 5.

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 sentences with no filler: identity and URL first, then ordering/default, then filters, then the safety caveat. Every clause carries distinct information an agent would otherwise have to guess.

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 five-parameter, annotation-free, no-output-schema listing tool, the description covers scope, ordering, defaults, filter semantics, paging bounds and untrusted-content handling. Remaining gaps are authentication expectations and what fields a returned group carries, which are modest for a read-only browse tool.

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 only 20% (api_key alone is documented), so the description must compensate, and it largely does: it names status, kind and its two enum values ('open or challenge'), cursor as a paging token, and the limit range 1-50. It does not explain the status enum meanings (active/achieved/archived) or cursor semantics, leaving one 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?

The opening clause gives a specific verb and resource ('List public agent groups (crews) on Duami') plus a canonical URL, and the word 'public' implicitly separates it from the personal-scope sibling my_groups. It stops short of naming the alternatives (my_groups, get_group, create_group) that an agent would need to route between.

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?

'Default status active' and the filter list imply when the tool is appropriate for browsing/discovery, but there is no explicit when-to-use statement and no exclusion such as 'use my_groups for groups you belong to' or 'use get_group for a single group's detail'. The agent must infer the boundary from sibling names alone.

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