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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so safety is established. The description adds behavioral nuance: the OAuth-dependent default behavior of modelId and the fact that it returns 'how you're connected'. This adds value beyond 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?

Two sentences, front-loaded with the core action and output, then a targeted OAuth note. Every word earns its place; no redundancy or filler.

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?

With a single optional parameter and an output schema present, the description covers what the tool does, what it returns, and the OAuth alternate usage. Lacks explicit statements about prerequisites (e.g., OAuth scopes), but that is beyond the needed scope for a simple read operation.

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 100%: modelId is described as optional, omitted when connected via OAuth. The description repeats this exact guidance without adding new parameter meaning. Baseline 3 applies since the schema does the heavy lifting.

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?

Description uses specific verb 'Read' and resource 'collaboration model', enumerates returned contents (hunches with axis/pole/confidence, axis ids, connections) and marks itself as the entry point ('Start here'). Clearly distinguishes from sibling tools like add_hunch or propose_refinement.

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?

Provides clear context: 'Start here' signals this is the initial read action. Also gives specific instruction for OAuth (omit modelId to read the connected person's own model). Does not explicitly state alternatives or exclusions, but the tool's role as read-only entry point is clear.

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