engineering-standards

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

With no annotations present, the description must carry the full burden of behavioral disclosure. The verb 'Retrieve' implies a read-only operation and the list of standards sets expectations for what can be fetched, but the description does not disclose the return format, error behavior, or whether the full standard text is returned, leaving some ambiguity for a tool with no output schema.

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 clear sentence followed by a necessary list of allowed values. It is front-loaded with the action and resource, and every word earns its place despite the unavoidable length of the standard list.

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 simple one-parameter get tool, the description adequately conveys what it does and enumerates all possible inputs. The only gap is the lack of detail about return content or output format, but that is minor for a retrieval tool and no output schema exists.

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%: the schema already defines the 'standard' parameter with a full enum and a description. The description repeats the same list of standards in prose, which adds readability but no new semantic meaning beyond what the schema already provides.

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 ('Retrieve') and resource ('a specific engineering standard'), and enumerates all 15 available standards. This clearly distinguishes it from the sibling review tools, which focus on branch names, commit messages, and staff engineer review rather than standard retrieval.

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 its usage by listing the valid standards, so an agent can tell it is for retrieving one of those named standards. However, it provides no explicit guidance on when to prefer this tool over the sibling review tools, nor does it state any exclusions or alternative routing.

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 are absent, so the description carries the burden. The verb 'Check' implies a non-mutating validation, and the specific conventions are stated. However, it does not disclose return format, whether it produces a report/boolean, or how failures are surfaced. This is a gap for a tool with no annotations and no output schema.

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 that states the action and the two key convention aspects. There is no redundant wording, making it highly concise.

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 tool is simple (one parameter, no nested objects, no output schema). The description covers the purpose and conventions, but the absence of an output schema and any mention of return behavior leaves an agent uncertain about the result format. Given the low complexity, this is a minor but real 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?

Schema description coverage is 100% for the single parameter, so the schema already documents branch_name. The description adds no additional parameter semantics beyond reinforcing that it's a branch name, but baseline 3 applies because the schema is complete.

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 ('Check') and resource ('git branch name'), and explicitly names the conventions checked (issue ID prefix, kebab-case). This clearly differentiates it from sibling tools like review_commit_message, which likely reviews commit messages, and get_standard, which may retrieve standards.

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 for validating branch names but does not explicitly state when to use it over alternatives, nor does it mention the sibling tools. The context (simple single-purpose tool) makes the usage clear, but there is no explicit exclusion or alternative 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?

With no annotations, the description carries the behavioral burden. It states what is checked and implies a read-only validation operation, but it does not disclose what the tool returns—whether it is a boolean, a list of violations, or a score—or how failures are reported.

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, tightly written sentence that front-loads the action and includes the most important details (the conventions being checked). No wasted words or redundant restatement of the tool name.

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 one-parameter validation tool, the description covers the essential check dimensions and is reasonably complete. However, the absence of an output schema and annotations means return behavior and usage context remain underspecified, leaving an agent to guess how to interpret the result.

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 only one parameter and the schema already describes it as 'The commit message to review' with 100% coverage. The description adds no meaningful semantic detail beyond what the schema provides.

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 ('Check if') and resource ('a commit message'), and enumerates the specific conventions checked: imperative mood, subject length, and structure. It distinguishes itself from review_branch_name by targeting commit messages, though it doesn't explicitly contrast with staff_engineer_review.

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 should be used when validating a commit message against conventions. However, it provides no explicit when-to-use or when-not-to-use guidance, and does not mention alternatives such as review_branch_name or staff_engineer_review.

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 carry the behavioral burden. It only says 'run through the checklist' and does not state whether the tool returns a checklist, evaluates the provided context, or has any side effects; output expectations are undisclosed.

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?

One sentence with no filler, and the main verb and resource are front-loaded. However, the phase list repeats schema information with less precision, so the space is not used as effectively as it could be.

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 no output schema and no annotations, the description is too thin to fully prepare an agent. It does not explain what the checklist output looks like, how the optional context parameter affects the result, or why one enum value is absent from the listed phases.

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%, so the schema already documents phase and context. The description adds only an approximate phase list that does not exactly match the enum and omits 'during_implementation', providing minimal additional meaning and some potential confusion.

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?

Clearly states it runs the staff engineer thinking checklist, and the phase list conveys the resource and intended scope. It is distinguishable from the sibling review tools, though 'given context' is vague and the phase labels are paraphrased rather than exact enum values.

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 parenthetical phase list gives some sense of when to use it: pre-code, pre-pr, post-merge, incident. However, it does not explicitly say when not to use it or contrast it with alternatives like review_branch_name or review_commit_message.

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