verdigraph

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

Since no annotations are provided, the description bears full responsibility for behavioral transparency. It discloses the deterministic nature (identical bytes produce identical brain_id), what is returned (brain_id, content_hash, counts, firing report, provenance), and the effect of include_document. It does not mention error behaviors, required permissions, or rate limits, but given the tool's nature, the provided details are adequate.

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 concise (3 sentences) with front-loaded main action. Information is presented in a bullet-like flow. It could be slightly more structured, but it efficiently conveys key points without redundancy.

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 complexity, absence of annotations, and presence of output schema, the description provides a solid overview of purpose, parameters, outputs, and an invariant. It is sufficient for an agent to understand the tool's function and when to invoke it. Missing details about request_id and potential errors are minor gaps.

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%, so the description must compensate. It explains 'content' as a file string, 'format' with listed options, and 'include_document' effect. However, 'request_id' is not described. This is good coverage for 3 of 4 parameters, adding significant meaning beyond the schema.

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 purpose: 'Compile an agent file into a deterministic, content-addressed brain.' It uses specific verbs ('Compile') and resources ('agent file', 'brain'). The tool is distinct from siblings (describe_agent, detect_format, verify_brain) which focus on description, format detection, and verification respectively.

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 lists possible format values and explains the include_document parameter, giving context for usage. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide conditions where it should not be used. Usage guidance is implied rather than explicit.

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 present, so the description carries the full burden of behavioral disclosure. 'Return' implies a read-only operation, but the description does not explicitly state side-effect profile, permissions, or context limitations. For a zero-parameter introspection tool, the risk is low, so a middle score is appropriate.

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?

At six words, the description is extremely concise and contains no filler. Every word earns its place, and the main action and target are front-loaded.

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 no parameters and an output schema exists, the description provides the essential information about what the tool returns. It is somewhat vague about the exact meaning of 'capabilities' and 'input contract', but the output schema likely fills that gap.

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 no parameter documentation to provide. The description correctly avoids adding parameter details; the baseline score of 4 for zero-parameter tools applies.

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 uses a specific verb, 'Return', and identifies the resource as 'capabilities and input contract', clearly stating the tool's function. However, it does not explicitly distinguish itself from sibling tools like get_agent or list_agents, so it falls short of a 5.

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 no guidance on when to use this tool versus alternatives such as get_agent or list_agents. It only states what the tool does, leaving the agent to infer when it should be selected.

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 must fully disclose behavior. It only states 'detect' without mentioning whether the tool is read-only, modifies state, or has side effects. This is inadequate for a tool with no annotation coverage.

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 that front-loads the action and lists examples. It is concise with no superfluous words.

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 covers the core purpose and usage timing, but lacks additional context such as error handling, prerequisites (e.g., content must be from an agent file), or behavior guarantees (e.g., no mutations). The presence of an output schema partially compensates for missing return value details.

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 0% schema description coverage, the description should add meaning to the 'content' parameter. It only uses the parameter name without specifying expected format, structure, or examples, providing minimal value beyond the schema.

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 verb 'detect', the resource 'content format', and lists four specific formats. It distinguishes from sibling tools (build_brain, describe_agent, verify_brain) by focusing on detection rather than construction, description, 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 phrase 'before building' provides clear context that this tool is a preparatory step. However, it does not explicitly specify when not to use it or describe alternatives, though the usage context is strong enough for typical use.

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. It discloses the deterministic recomputation and comparison logic but does not mention side effects, prerequisites, or behavior when no identifiers are provided.

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 effectively convey the core action and success condition. No wasted words, front-loaded with the key verb.

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 explains the main logic but lacks details on edge cases (e.g., when no identifiers are provided) and does not reference the output schema that exists, leaving some context incomplete.

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%, so the description must compensate. It clarifies the roles of brain_id and content_hash but does not explain the 'format' parameter or default values, leaving gaps.

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 specifies the verb 'verify' and resource 'brain', explaining the verification mechanism (recompute and compare). It distinguishes from siblings like build_brain (creation) and describe_agent (description).

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 explicit guidance on when to use or not use this tool vs alternatives. The purpose is implied but no when-to-use or exclusion criteria are given.

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