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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the description is free to add domain behavior: it states the 2026 RPM basis, discloses the default originality assumption ('unless told the footage is the creator's own ... it assumes reworked third-party footage'), notes that 'flagged earns 0', and warns output is 'rough ranges, not a promise'. It does not describe the shape of the returned estimate, which would have pushed this higher.

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?

Front-loaded with purpose in the first clause, then assumptions, then the disclaimer. Four sentences, no repetition. The trailing 'Pure math, rough ranges, not a promise. Free.' is terse but slightly fragmented marketing cadence rather than integrated prose.

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 5-parameter, nested-object tool with no output schema, the description supplies the platform scope, the assumption defaults, the failure case ('flagged earns 0'), and the output nature (USD monthly ranges). It stops short of describing the estimate's structure or uncertainty band, which an agent previewing the result would find useful.

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%, so 3 is the baseline, but the description explains the reasoning behind a key input: the originality enum's default of 'borderline' comes from Meta's March 2026 originality rule, and 'flagged earns 0'. That adds decision-relevant meaning the enum labels alone do not convey. Tier-mix normalization and niche defaults are left to the schema.

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 and resource ('Estimate monthly creator payouts (USD) for a view count') and enumerates the exact input dimensions (four platforms, audience tier, niche, originality) that define the tool. It is clearly distinct from the sibling estimate_credits, which audits credit spend rather than earnings.

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 stated: you feed it a view count and format and get an earnings estimate. It never names a when-not condition or an alternative (e.g. compare against estimate_credits for cost planning), and 'Free' hints at the economics but is not framed as routing guidance.

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