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

The description goes far beyond the annotations: it discloses that the tool runs a fresh (non-cached) analysis costing 5 credits, persists the new snapshot (mutation), returns only meaningful shifts, honestly returns status='no_meaningful_change' when nothing shifted, and returns a top_action pointing to the next tool. This paints a complete behavioral picture and aligns with the annotations (readOnly=false, idempotent=false), adding cost and state-change context the annotations don't convey.

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 longer than average but every sentence earns its place: purpose, mechanism, trigger phrases, prerequisite, cost, return behavior, and honesty note. It's front-loaded with the core purpose and mechanism, and while it could be tightened slightly, the density of useful information keeps it from feeling bloated.

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 complexity (it runs an analysis, persists state, and returns a rich result including a top_action), the description covers all decision-relevant information: trigger phrases, prerequisites, cost, return semantics (meaningful shifts vs. no_meaningful_change), and the existence of a top_action. The output schema defines the exact return structure, so the description doesn't need to list fields. Nothing an agent needs to decide whether and how to call it 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?

The schema already documents all three parameters at 100% coverage, so the description doesn't need to re-explain them. However, it adds one valuable piece of guidance: that watch_id is preferred over (platform, handle) because the ownership check is exact. This is extra semantics that helps the agent pick the right parameter, justifying a score above the baseline 3.

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 opens with a precise verb-resource pair ('Detect what changed since the last saved baseline for a tracked creator') and immediately differentiates it from siblings: it runs a fresh analyze_account under the hood, compares against a CreatorSnapshot, and returns only meaningful shifts. It even names the specific change categories (format, viral DNA, etc.), making the tool's purpose unmistakable and clearly distinct from analyze_account or watch_account.

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?

Explicitly lists trigger phrases ('what changed with @creator', 'anything new', 'check this competitor again') and states the prerequisite (a previously tracked creator, with a callout to call analyze_account + watch_account first if no baseline exists). This tells the agent exactly when to use the tool and what precondition must be met, which is strong usage guidance.

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