First-Call Witness

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

No annotations are provided, so the description must carry the full behavioral burden. It does not disclose whether the operation is read-only, how versioning works, whether there are permissions or rate limits, or what the response contains.

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 contains no wasted words. It is as concise as possible while still naming the action and resource.

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 zero-parameter tool the call itself is trivial, but with no output schema the description should explain what 'versioned budget table' returns. It leaves key details about the payload and versioning semantics unspecified.

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?

The tool has zero parameters, so there is nothing for the description to clarify. The baseline score for a parameterless tool is 4.

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 (Get) and resource (budget table), with the qualifier 'versioned' adding useful scope. It does not differentiate from siblings, but the siblings verify_receipt and witness_check are unrelated, so this is minor.

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?

No guidance is given on when to use this tool, when not to use it, or what alternatives exist. The only cue is the verb 'Get', leaving the agent to infer its role.

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?

No annotations are provided, so the description carries the full behavioral burden but discloses almost nothing: it does not explain what verification entails, whether the operation is read-only, what errors or outcomes may occur, or what permissions are needed.

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 a single front-loaded sentence with no redundant or wasted language. Its brevity is appropriate for the sentence itself, though other dimensions capture the missing detail.

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?

With a nested object input, no annotations, no output schema, and zero schema description coverage, the description is far too sparse to be complete. It omits what the receipt contains, what verification means, and what the tool returns.

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?

There is one required nested object parameter ('receipt') with 0% schema description coverage, and the description adds no meaning about its structure, required fields, format, or expected content.

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 ('verify') and resource ('signed receipt envelope'), making the tool's purpose clear. However, it does not differentiate from any sibling tool, though most siblings are unrelated.

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 no explicit guidance on when to use this tool versus alternatives, nor does it state prerequisites or exclusions. Usage is only implied by the tool name and one-line purpose.

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 must carry behavioral disclosure. It does disclose a constraint (paid work refused) and redirects payments to an HTTP endpoint. However, it omits critical traits: what the tool does, side effects, required permissions, and return behavior.

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 a single sentence, but it is not front-loaded with purpose. It spends its brevity on a payment constraint rather than the tool's core action. The structure is misleading: the main clause describes what the tool is not, not what it is.

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 one undocumented parameter, no output schema, and no annotations, the description is severely incomplete. It fails to explain the tool's action, the parameter's meaning, or when to use it versus siblings. An agent would have to guess to invoke it correctly.

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 for the single 'url' parameter is 0%—no description in the schema—and the tool description says nothing about what 'url' represents or how to format it. The agent is left guessing whether it's a witness URL, a callback URL, or something else.

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 only restates the tool name ('Witness check') and adds a payment constraint. It never states what the tool actually does—no specific verb, resource, or outcome. An agent cannot tell whether this tool verifies witnesses, checks witness availability, or something else.

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?

It implies a negative usage condition ('paid work is refused over MCP') but gives no positive guidance on when to call witness_check vs siblings like budgets or verify_receipt. The alternative surface (POST /check) is mentioned, but not framed as a tool alternative for specific tasks.

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