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

With no annotations, the description carries the full burden, and it does disclose useful behavioral traits: the fixed rule count, supported languages, and a ~12ms performance characteristic. However, it never states that the audit is read-only/side-effect free, whether it writes a report, or what permissions it needs.

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 with zero waste; the core verb and scope lead, and the detail (languages, latency) trails.

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 tool this covers the essentials, but with no output schema and no annotations the description leaves the return shape unexplained (what an audit result looks like) and omits any read-only/destructive signal an agent needs to call it safely.

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% and the single optional 'directory' parameter is fully documented in the schema, including its default. The description adds no syntax or format detail beyond that, so the baseline of 3 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?

States a specific verb ('Audits') and resource ('repository or directory') and quantifies scope (16 Clean Architecture & Security guardrails across five languages). This clearly distinguishes it from repoguard_fix and repoguard_diff, though it never names those siblings explicitly.

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 when-to-use guidance or routing to alternatives. An agent could infer this is the detection step versus repoguard_fix, but nothing in the text states that relationship, exclusions, or prerequisites.

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. It says what is audited but omits whether the operation is read-only, what permissions are needed, how results are reported, and whether it modifies the working tree.

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 with no wasted words. The purpose and timing appear immediately.

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 no-parameter tool, the core purpose is stated. With no output schema and no annotations, the description leaves gaps about return values, error behavior, and execution context, making it minimally adequate rather than fully complete.

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 takes zero parameters, so the baseline is 4. The description correctly adds no parameter information because none is needed.

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 and resource: auditing uncommitted git changes for architectural drift. The 'before commit' timing adds scope, but it does not name or contrast itself with siblings like repoguard_audit, so the agent must infer the distinction.

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?

Implies use before committing and on uncommitted changes, which gives some context. However, there is no explicit when-not-to-use guidance and no mention of repoguard_audit or other sibling alternatives.

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. It implies a non-mutating read (returns suggestions rather than applying fixes), which is useful, but says nothing about whether any files are touched, permission/auth needs, or how many suggestions are returned.

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 efficient sentence with no waste; the intent is front-loaded. It is perhaps slightly too terse for the tool's complexity, but nothing is padded.

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 only two simple parameters and no output schema, the description need not detail return values, but it also never characterizes the kinds of suggestions or scope of the analysis, leaving meaningful ambiguity for a tool whose name implies a stronger action than described.

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% with both required parameters fully documented (code content, filename with path examples), so the schema does the heavy lifting. The description adds no syntax or format detail beyond it, making the baseline 3 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 gives a clear verb and resource ('analyzes a code snippet and returns... refactoring suggestions'), but the tool name 'repoguard_fix' suggests code modification while the description only promises suggestions, a mild tension. It does nothing to distinguish itself from sibling repoguard_audit, which plausibly also analyzes code, so an agent cannot confidently route between them.

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?

There is no when-to-use, when-not, or alternative guidance. With three siblings (audit, diff, get_rules) that could each plausibly apply to a snippet, the absence of routing guidance is a real gap.

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 does disclose two behavioral facts beyond the schema: the count is fixed at 16 and only 'active' rules are returned (implying inactive ones exist but are excluded). It says nothing about return shape, whether the rules are cached/versioned, or permission requirements.

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 with no filler. The trailing rationale ('to prevent AI hallucination of invalid layering patterns') is arguably decorative, but it does convey why the ruleset exists.

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 no-parameter, read-only lookup with no output schema, the description is close to sufficient — the agent knows it gets the full active ruleset. Missing only the delivery format of the rules and whether the set is stable across calls.

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 takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool applies. The description correctly implies no filtering arguments — everything is returned unconditionally.

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 and resource ('Returns all 16 active architectural rules') with a scoping quantifier, so the agent knows exactly what comes back. It does not, however, distinguish itself from the sibling tools (audit, diff, fix), so the reader must infer the split from names alone.

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 purpose clause implies usage — fetch the ruleset before validating layering — but there is no explicit statement of when to call this vs. repoguard_audit or repoguard_fix, and no prerequisites or ordering guidance. Minimum viable context only.

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