capital.new mandate draft tools

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

With no annotations provided, the description carries the full burden. It adds meaningful behavior beyond the name: minting and revocation are 'human ceremonies at https://capital.new', and the version limitation about signing rails is disclosed. This gives the agent a realistic expectation of what the tool returns and its current constraints.

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 concise sentences: the first states the tool's core function, the second provides the ceremony details with a URL, and the third discloses a version limitation. No filler, front-loaded with the most important information.

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, no-output-schema info tool, the description is complete: it explains what is returned, where and how the ceremony happens, and notes a key limitation. Nothing necessary is missing given the tool's simplicity.

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 the baseline is 4. The description adds context about what the tool returns (the ceremony process) but doesn't reference parameters, which is unnecessary since there are none. The schema coverage is vacuously 100%.

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 opens with 'Returns where and how a mandate draft becomes an instrument', a specific verb ('returns') and resource (ceremony/mandate flow). It clearly distinguishes this tool from siblings 'mandate_draft_schema' and 'mandate_draft_verify' by focusing on the human authorization ceremony rather than schema or verification.

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 implies usage context: 'agents draft and verify; humans authorize' clarifies the role of this tool in the workflow, and 'v1 has no signing rail' warns of a current limitation. However, it does not explicitly state when to choose this tool over siblings, though the purpose distinction is clear enough.

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 full responsibility. It discloses significant behavioral details: v0 acceptance, inclusion of v0 template, output wrapper format, and that key order is part of the document. These are non-obvious and crucial for correct usage.

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 dense sentences, no filler. Each sentence adds necessary information: what is returned and how to wrap it. Excellent front-loading of purpose.

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?

This is a simple retrieval tool with no input. The description fully explains what it returns, how to use it, and critical formatting details. There is no ambiguity left for the agent.

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 baseline is 4. The description doesn't need to add parameter semantics, and it doesn't; it correctly focuses on the output and usage.

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 explicitly states the tool 'Returns the v1 Capital Authority Mandate draft template' and lists its components (never-delegable act list, digest convention). This clearly distinguishes it from siblings like mandate_draft_verify, which verifies drafts.

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 states the tool is for constructing a draft 'so an agent can construct a draft its principal will mint at capital.new'. This implies the usage context, but it does not explicitly mention when not to use it or alternatives beyond the sibling names.

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. It thoroughly explains the computation method (pretty-printed JSON, 2-space indent, key order preserved), the input variants (wrapped object or bare draft), and the limitations of what the verification proves. However, it does not mention what happens on digest mismatch or whether the tool has side effects, which would make it fully transparent.

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 and front-loads the primary action in the first sentence. The second sentence is dense but packs essential nuance about the verification scope and serialization format. Every sentence earns its place, though the long second sentence could be slightly restructured for easier scanning.

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?

The description lacks any mention of the tool's output or return value. Since there is no output schema, the description should indicate what the tool returns (e.g., boolean, match/mismatch, or error details). For a verification tool, the result is the core purpose, so omitting it leaves a significant gap. The input handling is well covered, but the output is absent.

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 schema already documents the parameter with 100% coverage, but the description adds valuable semantic detail: 'Accepts the wrapped {mandate_draft, digest} file or a bare draft.' This clarifies the accepted shapes beyond the schema's anyOf object/string, making it easier for the agent to construct valid input.

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 the tool's function: 'Recomputes the SHA-256 digest... and compares it to the digest embedded in the file.' It goes beyond a simple verb+resource by explaining exactly what the verification establishes and what it does not, effectively distinguishing it from sibling tools related to ceremonies and schema.

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 for when to use the tool by explicitly stating its scope: 'Establishes that the file is internally consistent... NOT that it was minted, and not that capital.new has ever seen it.' This exclusion of provenance claims is a form of when-not-to-use guidance, though it does not name alternative tools directly.

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