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

Annotations already cover safety (readOnlyHint, idempotent, non-destructive, closed-world), and the description adds real context beyond them: the subscription/record prerequisites and a concrete enumeration of what is produced. It does not mention generation time, file size, or whether repeated calls overwrite anything, which matters for a multi-file export.

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 sentences, front-loaded with purpose and returns, then prerequisites, then the routing fallback. The opening phrase 'One company's company record' is slightly awkward but no sentence is wasteful.

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?

With no output schema, the description correctly enumerates the return artifacts (CSV set, research notes, import steps) and states both preconditions, which is what an agent needs to call it safely. Only minor operational details (size, timing, multi-company behavior) are absent.

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% and the enum is already declared, so the description's restatement of 'format (hubspot or salesforce)' and 'must already have a company record' adds nothing new. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Names a specific verb+resource ('One company's company record as CRM import files') and states the two inputs and the three deliverables (CSV files, research-notes document, import steps). An agent can distinguish it from deep_record, company, and find without opening the schema.

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?

Gives concrete preconditions ('Requires an existing company record and an active Whimbrel plan') and routes the no-record case explicitly to deep_record. It does not state any case where this tool should not be used despite having a valid record, so it stops short of full when/when-not coverage.

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