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

With no annotations provided, the description carries the full behavioral burden. It discloses the composite pipeline, the conditional generate-vs-refine path, optional agent profiling from writing samples, and the full return payload including 'draft_was_generated,' scoring breakdowns, rewrites, and one_thing. It does not mention the default scoring-skip/latency behavior in the description itself, which is left to the include_scoring schema.

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 one-sentence purpose is front-loaded, and the Returns block is organized and scannable. The composite-tool explanation is valuable for a tool this complex, though the bullet list is long enough that some redundancy with the output schema and parameter descriptions exists.

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 12-parameter composite tool with no annotations, the description covers the main input-to-output flow, the generate-vs-refine conditional, and the intended CRM context, and it lists the key return fields. The main gaps are the purpose of name/title/company/industry and the default scoring behavior, though the input schema and output schema partially fill those gaps.

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 67%, so the description must add some meaning, and it does. It ties audience_description to OCEAN/ELM/Cialdini profiling, writing_samples to agent profiling, and the absence of a draft to automatic generation. The name/title/company/industry parameters remain implicit, but their role is inferable from the CRM-prospect framing.

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 phrase and resource: 'Generate or refine a personalized cold email for a CRM prospect.' It then distinguishes itself from the sibling analyzer tools by explicitly labeling itself a composite tool that combines audience profiling, agent profiling, draft generation, and persuasion/platform scoring in a single call.

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?

It clearly states the intended context: 'Designed for CRM integrations like Clarify, HubSpot, Salesforce — pass a Person/Account context, get back a draft + scoring.' It also implies when to use it over the component siblings by calling itself a composite tool. It does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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