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

With no annotations provided, the description carries the full burden—and it excels. It discloses that offers are 'QUARANTINED', require a 'NAMED HUMAN' to choose before a card is created, and that 'There is no path around the comb' (no bypass). It also states constraints: only public-domain/openly-licensed sources, never generated text, and attribution via agent label. These are significant behavioral traits beyond the schema.

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 description is a single dense paragraph that front-loads the primary action, then adds crucial caveats and workflow details. Every sentence contributes—constraints, quarantine, human selection, no bypass. The use of metaphor ('comb', 'forager', 'shaft-tag') adds flavor but requires interpretation, slightly reducing conciseness; otherwise it is well-structured.

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?

The description adequately covers the tool's core workflow and constraints, which is the key context given the tool's complexity (quarantine, human approval). It does not describe return values or error conditions, nor does it explain the 'comb' metaphor for new agents. The 'domain' parameter is also omitted. Still, the description is sufficiently complete for an agent to understand the intended use and workflow.

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 low (17%, only agent is described). The description compensates by explaining the roles of label, url, and snippet ('label + url + snippet, attributed'), and implies the agent is the attribute tag. It also implicitly references want_id via 'open want'. However, the 'domain' parameter is not addressed, and the description doesn't provide format or constraints for individual parameters beyond their roles.

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 description states a specific action: 'Return to the comb with a FOUND source for an open want: label + url + snippet, attributed.' This clearly identifies the tool's purpose—offering a located source for an existing want—and distinguishes it from sibling tools like want_open (which likely opens wants) and wants_list (which lists them). The core action and resource are unambiguous despite the metaphorical 'comb'.

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?

Usage is implied rather than explicitly stated. The description makes clear that this tool is for submitting a source you've actually found, and it contrasts 'forager' vs 'author' to indicate when it's appropriate (only with real, openly-licensed sources). However, it does not name alternatives or provide explicit 'use when / don't use when' guidance, and no sibling references appear.

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