get_evidence_recipeFor one obligation, return exactly how to prove it: which sources settle the question, which are only corroborating, what each state's public registry does and does not expose, and the innocent explanations for missing evidence. Use this before concluding anything is missing.
| Name | Required | Description | Default |
|---|---|---|---|
| obligation_id | Yes | Obligation id from list_compliance_obligations. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds substantial behavioral context by detailing the exact nature of the output: which sources settle, which are corroborating, what registries expose, and innocent explanations. This goes beyond what annotations provide, giving the agent a clear picture of what to expect.
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 description is two sentences, front-loaded with the primary action and object. Each clause adds value—scope, output content, and usage timing. There is no filler or repetition of schema details.
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?
Given the tool has one simple parameter, good annotations, and no output schema, the description carries the full burden of explaining the return content. It does so thoroughly, listing specific categories of information the recipe includes. It also provides a contextual usage pointer. This is complete for the tool's complexity.
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 sole parameter (obligation_id) is already clearly described as 'Obligation id from list_compliance_obligations.' The description only adds 'For one obligation,' which is redundant with the parameter name and schema. No additional syntax or semantics are provided, so the baseline of 3 is appropriate.
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 clearly states a specific action: 'For one obligation, return exactly how to prove it.' It identifies the resource (evidence recipe for an obligation) and enumerates the content (sources that settle, corroborating sources, registry exposure, innocent explanations). This distinguishes it from sibling tools like explain_obligation or get_confounders by focusing on evidence and proof.
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 provides clear context on when to use the tool: 'Use this before concluding anything is missing.' This implies a specific workflow step. However, it does not explicitly name alternatives or state when not to use this tool, so it stops 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.
Add one secure layer between your agents and this server.
Tools mostly demand exactly one job: the list/explain/score path is clearly labeled per domain, and the START-HERE markers guide entry points. The fuzzy spots are get_conf_lefts and get_evidence_recipe (both refinement steps after list_compliance_obligations) plus list_services vs get_company_overview (they overlap on what Median does); these are distinguishable from the descritions but are the kinds of pairs that could send an agent the wrong way.
All twelve names follow the same verb_noun snake_case convention with consistent verbs: list the collections (_lists), get facts/computed refinements, explain single-item detail, and score the assessment. The pair structure (list vs explain vs proof) makes the intent predictable from the name for the first decode.
Twelve tools is right within the ideal for a domain-focused server: seven true domain tools (compliance + books) and five content/take-usational helpers. The content cluster (services, overview, pricing, blog, blog_post) is a bit tangential to a compliance/books mission, but this is a company-fronting server, so the zone works with a reason.
Both workflows close their loop: compliance has list → explain → confounders → evidence, and books has list → explain → score, with no obvious dead-end in either. Minor residuals exist (no explicit tool for showing covered versus non-covered states, other collaboration across the two domains), but an agent can work out these as of today's.