Agent Preflight

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety bar is met structurally. The description adds genuinely useful context beyond that: it guarantees the URL is never fetched (no side effects at all) and explains that the optional economics input produces proceed/abort advice derived from expected waste versus a $0.002 check. It does not cover auth requirements, latency, or failure modes, so it stops short of a 5.

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 sentences, front-loaded with the core action, then the non-execution caveat, then the optional economics behavior. Every sentence carries information and there is no filler, though the final sentence is dense and could be split or simplified.

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?

An output schema exists, so return values need not be described, and the description covers purpose, the no-execution guarantee, and the optional economics mode. For a read-only validation tool this is nearly complete; the remaining gap is disambiguation from preflight_tool_call, which the description ignores entirely.

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 67% and the parameters are nested, so the schema already documents most fields including url, method, headers, query, and the individual economics properties. The description adds only a high-level gloss on what the economics block is for ('proceed/abort advice from expected waste versus a $0.002 check'), without clarifying defaults such as preflightPriceUsd or priorInvalidProbability. This is a baseline 3 with modest added value.

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 states a specific verb and resource: validate an HTTP API request body against a supplied JSON Schema, and explicitly bounds the scope with 'This tool does not execute the request.' It is clear and unambiguous, but it never mentions the sibling tool preflight_tool_call, so an agent cannot tell them apart from the description alone.

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?

'Use it when an agent needs to determine whether a proposed JSON body satisfies its expected schema' gives a clear triggering condition, and 'does not execute the request' implicitly rules out using it as a send/fetch step. However, no alternative tool is named and no when-not condition relative to preflight_tool_call is offered, which matters given the overlap implied by the sibling name.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description nonetheless adds real behavior: the caller must supply cost estimates and history, executes the tool and fetches resultReference itself, estimates are hypothetical rather than receipts, confidence is uncalibrated, and paid HTTP costs $0.002 per settled POST. That is substantive context beyond the annotations.

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 dense sentences, front-loaded with what the tool is and what it does not return, with the contract link last. Every sentence carries information, though the semicolon-chained clauses and unexpanded acronyms make it read more like a spec fragment than a clean guide.

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?

An output schema exists, so return-value explanation is correctly omitted. Given the complexity (10 params, nested objects) the description covers scope, cost model, reuse conditions and the contract URL adequately, with the main remaining gap being differentiation from the check_request sibling.

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?

With 10 parameters and 0% schema description coverage, the description must carry the load and only partially does: it maps to estimated cost, budget, history, goalHash, freshness TTL and reuse permission, but says nothing about runId, stepId, tool.provider/operation/request, retryCap or preflightPriceUsd. It adds meaning for roughly half the surface.

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 states a specific function: a free preflight decision on proposed generic search:web_search or browse:fetch calls that returns a decision payload rather than destination results. It is recognizable and scoped, but heavy jargon ('Free MCP decision') and the absence of any contrast with the sibling check_request leave the boundary slightly fuzzy.

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?

Scope is implied by 'generic search:web_search or browse:fetch proposals only,' and reuse conditions are spelled out (explicit permission, positive TTL, matching nonempty goal hashes), but there is no explicit when-to-use versus check_request or when-not guidance. The paid-HTTP note hints at an alternative interface without naming it.

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