Matches an explicit need to a referral service, rejects unsafe scope, and prioritizes existing, local, or free solutions over paid ones.
Match an explicit need to capability; reject unsafe scope, prefer existing/local/free. Budget is not authorization. No commission-based ranking.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose real behavioral policy — no commission-based ranking and that budget is not authorization — which is valuable, non-obvious context. However, it never states whether the tool is read-only/advisory, whether it actually creates a referral, or what it returns, leaving side-effect profile unstated.
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 clauses, front-loaded with the core matching rule and followed by the two hard constraints. No filler, though the aphoristic phrasing ("Budget is not authorization") costs some clarity in exchange for brevity.
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?
No annotations, no output schema, and a seven-field nested request at 0% schema description coverage — this is the case where the description should do the most work. It omits the return shape, how sensitive_or_login_required and sources_permitted change the recommendation, and any precondition for obtaining consent before referrals.
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 nested Selection has seven fields, so compensation is needed. The description does add meaning to a few: "explicit need" maps to need, "prefer existing/local" maps to existing_solution_sufficient/local_solution_sufficient defaults, and "budget is not authorization" clarifies maximum_monthly_budget_usd. But the six-value need enum, sources_permitted, recurring_need, and sensitive_or_login_required go entirely unexplained.
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?
"Match an explicit need to capability" gestures at recommending a provider for a stated need, but the verb is abstract and never names the artifact produced (a ranked recommendation vs. a single provider). It does not distinguish this from siblings like list_referral_providers or assess_browseract_fit, so the agent must infer the boundary.
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?
"prefer existing/local/free" and "reject unsafe scope" give decision policy for ranking, which implies when this tool applies. But there is no explicit when-not guidance and no mention of the sibling tools, so routing between recommend_referral_service and list_referral_providers is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.