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

Annotations already declare idempotentHint=true and readOnlyHint=false, but the description adds substantial context beyond them: the exact cost model (0 credits on cache/watch reuse, 5 credits on a fresh baseline), the credits_charged=0 return signal, and reuse of the existing 'analyze' OAuth permission with no re-consent. This is richly disclosed behavioral detail an agent needs.

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?

Six sentences, all earning their place, with the core purpose front-loaded followed by usage triggers, idempotency, cost, and permissions. Slightly dense, but no wasted filler and information is ordered by importance.

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 tool with an output schema, the description need not explain return values; it covers everything else an agent needs — purpose, triggers, idempotency semantics, cost, and auth implications. Nothing material is missing.

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 100% and both parameters (handle, platform) are fully documented in the schema, including format examples and enum values. The description references 'watch @same' but adds no syntax or format detail beyond what the schema already provides, so the baseline 3 applies.

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+resource ('Start tracking a creator') and immediately names the artifacts it creates (durable CreatorWatch + baseline CreatorSnapshot). Distinguishes itself from siblings like analyze_account, list_watches, and get_changes by describing what it produces rather than merely restating its name.

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?

Gives explicit trigger phrases ('track', 'watch', 'follow', 'keep an eye on'), states idempotency conditions, and identifies the relationship to analyze_account (which it invokes for a fresh baseline). The agent knows both when to call it and what it will cost.

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