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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it explains the return shapes (ClimbSnapshot[] with chain, or no_evidence_available with reason), and the limits (max 200 snapshots, limit cap 1000). This goes beyond annotations, though it doesn't elaborate on potential performance implications or edge cases (e.g., what happens if since is invalid).

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 dense but well-structured: it front-loads the core behavior, then details the return shapes, then lists parameters, then an example. Every sentence adds value without repetition. It's a single paragraph but logically organized.

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?

Given the tool's moderate complexity (3 params, no output schema, no nested objects), the description is complete for an agent to invoke it correctly: it covers defaults, limits, param formats, return kinds, and error handling. It even provides an example call. No gaps identified.

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 full param burden. It explains all three parameters: since=ISO timestamp, limit=integer ≤1000, repo=string. It also adds context on defaults (window 7 days, max 200 snapshots, default repo) that aren't in the schema. This is excellent compensation for the schema's sparse documentation.

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 clearly states this is a time-series read of honesty-ratio snapshots for a federation, with a specific verb (read/climb history) and resource (windows of snapshots). It distinguishes from siblings by specifying the introspection_system prefix and contrasting with other introspection tools (e.g., list_nodes, diff) and federation tools.

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?

The description gives explicit usage context: default window is last 7 days, max 200 snapshots, default repo is 'comai-plan', and it explains when to pass a different repo id. It also specifies when it returns no_evidence_available, which helps the agent decide when to use this tool vs alternatives like list_nodes or list_repos.

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