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

Annotations only declare the safety profile (non-read-only, non-idempotent, non-destructive, closed-world); the description goes beyond them with the credit-per-person billing model, the free-reuse caching behavior, and the confirm_action gating requirement. These are exactly the operational traits an agent needs before spending credits.

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?

Three tight sentences: what it produces, what it costs, when it may run. Every clause carries information and the most important gating constraint is not buried.

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 and one input, the description covers the deliverables, the cost model, and the prerequisite well. It leaves minor gaps around what happens on partial failure or whether previously generated research is overwritten.

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% and the single required parameter prospect_ids is never mentioned in the description. 'Per person' hints that cost scales with the number of prospects, but nothing explains the ID format, whether IDs come from search_prospects, or the batch behavior.

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 (prepare research) plus the exact artifacts produced: sourced facts, icebreaker, connection note, LinkedIn message and email. This clearly separates it from retrieval siblings like get_prospect_research and enrichment siblings like enrich_prospects.

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 a hard prerequisite ('Runs only after confirm_action') and cost context ('Costs credits per person; fresh research is reused free'), which tells the agent when it is safe and cheap to call. It does not explicitly contrast with get_prospect_research or enrich_prospects, so an alternative-selection sentence is missing.

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