DiffCI

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

Annotations already establish that the tool is read-only, idempotent, and non-destructive, so the description does not need to repeat those traits. It adds meaningful behavioral context by specifying what validation covers (mode, affected-test counts, fallbacks, non-interference evidence) and what the output includes (a conservative next action). No contradiction with annotations exists.

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?

A single, front-loaded sentence states the core action first ('Validate and summarize a DiffCI observation report') and then enumerates the relevant dimensions in a compact list. There is no filler or redundancy, and every clause earns its place.

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 required parameter, full schema coverage, and safety annotations, the description covers the main purpose, the report content of interest, and the nature of the output (summary plus conservative next action). It does not describe error conditions or detailed output structure, but those are not explicitly required given the absent output schema and the tool's relatively narrow scope.

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 100% with the parameter documented as 'A diffci.observation.v1 JSON report,' so the schema already identifies the type. The description adds value by listing the salient report aspects the interpretation centers on, giving an agent a better model of what the report object is expected to contain beyond the bare type label.

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 specific verbs ('Validate and summarize') tied to a clear resource ('a DiffCI observation report') and enumerates concrete report facets (selective/full mode, affected-test counts, fallbacks, non-interference evidence, conservative next action). This clearly distinguishes it from siblings like diffci_validation_plan and diffci_verify_workflow_text, which involve planning and verification rather than report interpretation.

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 the tool is used when an agent has a DiffCI observation report and needs it validated/summarized, but it gives no explicit when-to-use or when-not-to-use guidance, and it does not mention alternative sibling tools. The usage context is inferable rather than stated, so it stops short of strong guidance.

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?

The description meaningfully supplements the annotations: beyond readOnlyHint and idempotentHint, it discloses that the tool does not access the checkout and does not execute the command. This is valuable context for an agent deciding whether the operation is safe and side-effect-free.

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?

A single dense sentence covers the core purpose, scope, and key safety behavior. It is front-loaded with the main action and resource, and no words are wasted.

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 is sufficient for a low-complexity, read-only planning tool: it states what is planned, what is returned, and the safety boundary. The lack of an output schema is mitigated by the explicit statement that a safe local DiffCI command is returned.

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 100%, so the schema fully documents all three parameters. The description adds no parameter-specific detail beyond the general context of planning validation actions, but it does not need to compensate for a documentation gap.

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 action ('Plan') and a clear resource (change-aware CI validation, affected-test selection, test impact analysis, GitHub Actions workflow checks), and clarifies that it returns a command rather than executing work. It does not explicitly contrast with the sibling tools, but the purpose is specific enough to avoid confusion.

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 when to use this tool: when you need to plan or validate CI changes locally and get a safe command without checkout access or execution. However, it does not explicitly mention alternatives or state when not to use it, so usage guidance is only 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?

Annotations already declare readOnlyHint=true and idempotentHint=true; the description adds 'stateless', which aligns with these hints, and enumerates the specific checks performed. This goes beyond annotations by clarifying the scope of the verification without contradicting any annotation.

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, compact sentence that front-loads the action and then lists the check items in a clear list. No fluff or redundancy; every word contributes to the tool's 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?

The description explains what the tool does and its stateless nature, but it does not mention what the tool returns (e.g., pass/fail, report) or any error conditions. With no output schema and a single parameter, a bit more context about the result would improve completeness, though annotations cover safety aspects.

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 100% (the 'workflow' parameter is described as 'One GitHub Actions workflow YAML document.'). The description does not add additional detail about the parameter format or constraints, so it provides no extra value beyond the schema. Baseline 3 is appropriate.

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 action: 'Perform a stateless preliminary safety check of GitHub Actions YAML' and lists specific aspects (dedicated observer job, continue-on-error, dependency isolation, read-only permissions, immutable DiffCI references). It distinguishes this from sibling tools by focusing on verification rather than interpretation or planning.

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 word 'preliminary' implies this is an early-stage check, but it does not explicitly say when to use this tool instead of diffci_validation_plan or diffci_interpret_report, nor does it state exclusions. The usage context is implied rather than explicitly contrasted with alternatives.

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