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

Annotations already declare read-only, idempotent, non-destructive behavior, yet the description still adds real operational context: plain-text output, placeholder substitution for missing fields, draft-only with legal-review caveat, free/no-auth access, and rate limiting. That is meaningful disclosure beyond the structured hints.

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?

Four short, front-loaded sentences with no filler; the core action leads and constraints follow. Compact for the amount of behavioral context conveyed.

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?

An output schema exists so return format need not be described, and the draft/placeholder caveats are useful. But for a 10-parameter tool with zero schema descriptions, the absence of any parameter guidance leaves an agent guessing about inputs it must supply.

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% across 10 parameters, so the description must carry the load, and it does not. It only notes that missing text fields become placeholders; it explains nothing about what includedScope, overageRate, providerName, or the enum-backed terms actually control.

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: 'Generate the website's monthly retainer agreement as plain text.' That clearly separates it from sibling document generators like coaching_agreement, sow_generate, or quotation_generate. No explicit sibling routing, but the document type is unambiguous.

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 by the document type and reinforced by 'Draft only; legal review may be needed,' which sets expectations for a generated draft. However, it never states when to pick this over, say, sow_generate, nor any prerequisite or exclusion conditions.

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