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

With no annotations, the description carries the full burden and does disclose key behavior: there is NO session state (ADR 0038), org/slot bindings/connector identities derive from the token, and it returns connector overrides. It stops short of describing error cases or what a failed resolution looks like.

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 purpose is front-loaded, but the prose is jargon-dense (ADR 0038, PRE-MADE, RELIABLE in caps) and mixes resolver description with workflow instructions for other calls, which blurs the structure.

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?

No output schema exists, and the return is only described as 'connector overrides' without saying what that contains or how to use it. For a resolver tool gating access to a project it is adequate but leaves an agent short of what to expect back.

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 0%, so the description must compensate. It explains project_id's origin (oto_project op=list) but says nothing about the optional `_org` parameter or the integer type/format expectations, leaving half the parameters undocumented.

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: 'Resolve a project you can access' and names its output, 'Returns the project's connector overrides.' The purpose of resolving versus listing is inferable, though the interleaved guidance about passing `project=<id>` elsewhere muddies the core statement.

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?

It names the prerequisite source of the id ('project_id from oto_project op=list') and instructs passing `project=<id>` on each work call, which is real usage guidance. But it never contrasts this with sibling scoping tools like oto_use_org or oto_use_group, nor says when-not to call it.

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