Tool-result size governor for MCP

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

With no annotations, the description carries the full burden, and it does disclose real behavior: byte-exact retrieval, checksum re-verification, and that unknown_artifact is a clean error. It omits offset/limit boundary behavior, pagination semantics, and any auth or rate-limit context, so it is helpful but incomplete.

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?

Two short sentences, front-loaded with the core action and followed by the integrity guarantee and error case. Nothing is padded, though the terseness borders on cryptic for jargon like 'spilled payload'.

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 3-parameter tool with no annotations and no output schema, the description covers the purpose, integrity guarantee, and one error case, but leaves limit/offset semantics and slice-size defaults unaddressed, so an agent could still mis-invoke it.

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% for three parameters. The description hints that the call produces a 'narrower slice' (mapping loosely to limit/offset) and references artifact_id via the unknown_artifact error, but gives no format, units, or boundary meaning for any of the three.

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+resource: re-fetching a narrower slice of your own spilled payload. The 'your own spilled payload' framing implicitly separates it from shape_result and verify_receipt, though it doesn't name them explicitly, so it falls just short of the top band.

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?

Usage is only implied: 'narrower slice of your own spilled payload' tells the agent this follows a prior spill and narrows it, but there is no explicit when-to-use, when-not, or named alternative among the siblings. Adequate but leaves routing to inference.

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?

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: per-result pricing, an X-PAYMENT header requirement, a 100-result free trial, and the fact that output includes a signed omission receipt (implying truncation). It still omits what gets omitted or discarded, whether shaping is reversible, and any auth requirements beyond payment.

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?

Two sentences, front-loaded with the action and outputs before the pricing clause, with no obvious filler. It is compact for the amount of information conveyed, though the arrow notation is terse to the point of ambiguity.

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 tool with six undocumented parameters, nested objects, no annotations, and no output schema, the description is far too thin. An agent cannot determine what to put in args, result, tool_args, or fixture_tool from this definition alone.

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% across six parameters, including nested objects (args, result, tool_args), so the description must compensate and largely does not. 'Per-route budgets' weakly hints at the required 'route' parameter, but args, text, result, tool_args, and fixture_tool are entirely unexplained in both schema and description.

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 verb ('Shape') and resource ('one tool result') and names the outputs ('shaped window + signed omission receipt'), so the general action is inferable. However, 'shape' is opaque jargon that is never defined, and the description never distinguishes this from the sibling tools fetch_slice and verify_receipt, leaving the agent to guess the division of labor.

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?

There is no guidance on when to call this versus fetch_slice or verify_receipt, nor on prerequisites (e.g., that a route must be configured with budgets). The only context given is pricing and trial terms, which describe cost, not usage conditions.

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?

With no annotations, the description carries the full burden of behavioral disclosure, and it barely does so. It does not state whether verification is a read-only operation, what happens on a failed or malformed signature, whether it throws versus returning a result, or any authentication/rate-limit requirements.

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 single sentence is front-loaded and free of filler, so it is structurally clean. But at this length it reads as under-specification rather than deliberate conciseness, since a non-trivial cryptographic verification tool needs more substance.

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 a nested-object parameter with zero schema descriptions, no output schema, and no annotations, the description omits nearly everything an agent needs: the receipt's shape, the meaning of a successful/failed verification, and the return value. It is not adequate 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 0% and the single parameter is an opaque nested object with no documented properties. The phrase "signed omission receipt" hints at what the object contains, but it gives no field names, expected encoding, or format, so an agent cannot construct the argument without guessing.

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 pairs a clear verb ("Verify") with a named resource ("signed omission receipt"), so the general action is identifiable. However, "omission receipt" is unexplained domain jargon and the description offers nothing to distinguish this tool from siblings like fetch_slice or shape_result, leaving the purpose only partially clear.

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?

There is no guidance on when to use this tool, what preconditions apply (e.g., where the receipt came from), or what to use instead for related tasks. Usage can only be inferred from the single word "Verify" in the description.

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