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

Annotations only indicate non-read-only and non-destructive, which is minimal. The description goes far beyond by disclosing cost ('about 353 credits (~$0.353) per call'), speed ('slowest, typically 30 to 60 seconds'), and internal process ('Runs a 5-step drafting pipeline'). It also clarifies the output nature (the letter itself, not advice). This is rich behavioral context that annotations do not cover.

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 compact yet information-dense: a one-line purpose, a condition clause, an output clarification, a process note, and a cost line — all in a few sentences. It front-loads the primary purpose and then covers essential operational details without fluff. Every sentence earns its place.

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 drafting tool with 11 parameters (all well-described in the schema) and an output schema absent, the description covers the key contextual needs: what it generates, when to invoke it, cost, speed, and output tone. It does not need to repeat parameter semantics. The description is complete enough for an agent to call it correctly and anticipate consequences.

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%, meaning every parameter already has a detailed explanation (e.g., appealType enum semantics, status categories, naturalness scale). The tool description adds no additional parameter-specific guidance beyond what the schema provides, so the baseline of 3 is appropriate.

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 specific verb and resource ('Draft a financial aid appeal letter to a college financial aid office'), immediately clarifying what the tool does. It also provides concrete trigger examples (income dropped, expense appeared, competing offer, FAFSA error) that distinguish it from analysis or advisory tools, making its purpose unmistakable.

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 explicitly instructs when to call it ('Call this when a family needs to ask for a review of an award') with specific scenarios, and it states a clear exclusion ('Returns the letter, not advice on whether to appeal'). It does not explicitly name alternative sibling tools (like letterlens) for when not to use it, but the given triggers and output clarify the appropriate context well enough.

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