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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the bar is lower and the description earns credit for adding context beyond them. It discloses the cost model ('included in Pro, or €0.10 per call over MPP if you have no key'), the data-coverage probability (~96% of funds carry signals), and the failure/billing behavior (not_found returned BEFORE payment, so a wrong slug is never charged). This is exactly the kind of behavioral disclosure agents need and is not present in any structured field.

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 purpose is front-loaded in the first sentence, followed by return contents, usage context, then cost and failure behavior. Every sentence earns its place — the cost and not-found details are unusual but valuable for a paid tool. It runs slightly long with the cost sentence being somewhat detailed, but nothing is filler. Well-organized density without waste.

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 single-parameter read-only tool with no output schema, the description is remarkably complete: it enumerates the return contents (compensating for the missing output schema), explains the input provenance, gives usage timing, discloses cost, data availability probability, and the no-charge-on-not_found guarantee. Nothing an agent needs to invoke this correctly and safely is missing.

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% — the schema's slug description already explains the provenance ('exactly as returned in the slug field of search_funds') and instructs the agent to call search_funds first rather than guessing. With high coverage, the baseline is 3, and the description text adds no additional parameter meaning. The schema fully carries the load for this single parameter, so no penalty, but also no credit beyond baseline.

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+resource ('DRILL DOWN on a fund') and enumerates exactly what the tool returns: GP thesis, bullish/contrarian signals, founder dos and don'ts, deployment status, and source URLs. It also distinguishes itself from siblings by scoping to funds 'you already identified with search_funds or get_fund', which sets it apart from search_funds (discovery) and get_fund (basic info). An agent can tell what this does 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?

The description gives clear when-to-use context: use it after identifying a fund via search_funds or get_fund, and specifically 'before writing an outreach message to a specific fund.' It implies the workflow sequencing (search first, then drill down), but stops short of explicitly naming exclusion cases or routing to an alternative sibling (e.g., 'for GP background use get_gp_profile instead'). Clear context without formal exclusions earns a 4.

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