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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered by structured data. The description adds genuinely useful behavioral context beyond that: the return shape and the explicit note that raw regexes are intentionally withheld, which prevents an agent from hunting for them.

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 of purpose followed by a compact return-shape block; nothing is padded. The purpose is front-loaded and the structured detail follows it logically.

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 present, the description carries the return-value burden and does so concretely (count, patterns with name/severity/advice, entropy_detector, allowlist_rules). It also closes the obvious follow-up question about regex exposure, so an agent has everything needed to call and interpret this tool.

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, which is the baseline-4 case. There is nothing to disambiguate and the description correctly implies a no-argument listing call.

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 precise verb and resource ('List the active secret detectors and allowlist rules'). This is clearly distinct from the sibling scan_* tools, which perform scanning rather than config introspection, so an agent can route correctly without opening the 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 purpose implies this is for discovering what detectors exist, but the description never states when to prefer it (e.g., before a scan to know coverage) or names any alternative. Usage is inferable but not spelled out.

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 establish readOnly, idempotent and non-destructive, so the description focuses on what it adds: everything non-secret is preserved verbatim, and the result includes a redaction count plus a per-detector breakdown. That is meaningful context beyond the structured fields, though nothing is said about failure modes or text size limits.

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 opening two sentences are well front-loaded and earn their place. The trailing Args and Returns blocks largely duplicate the input schema and the existing output schema, which is wasted text for an agent that already receives both.

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 pure transformation with full annotations and an output schema, the description covers purpose, usage and preservation semantics. The redundant Returns block is the only real flaw; nothing an agent needs to invoke it correctly is missing.

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 a single parameter with 0% schema description coverage, so the description carries the whole burden. 'text: The text to clean' restates the parameter name and adds only that cleaning means secret substitution, which is already implied by the summary. Adequate but thin.

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 precise verb and resource — return the text with every detected secret replaced by [REDACTED:<detector>] — and names the exact output format. It implicitly separates itself from the scan_* siblings (detection only) by producing a cleaned copy, though it never names an alternative tool 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?

It gives concrete call-site guidance: use it before quoting logs, stack traces, configs, command output or diffs in a conversation, issue, commit message or document. That is clear context for when to reach for it, but there are no exclusions and no pointer to the scan_* tools for the detect-only case.

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 readOnly, idempotent, and non-destructive, so the description adds real context: it reports whether git tracks a project config (a key in a tracked .mcp.json ships with the repo), orders findings by severity, and flags that transcript scanning is slower and off by default. It stops short of saying what the report contains beyond the agent_files array.

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?

Front-loaded one-line purpose followed by scope, per-parameter notes, and return shape. The client enumeration is long but each item expands coverage meaningfully; no sentence is filler.

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?

An output schema exists, yet the description still names the key return field (agent_files) and its members, and covers all four optional parameters and their defaults. Nothing an agent needs to invoke or interpret this scan correctly is missing.

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 carries the full burden and does: project_path is identified as an optional absolute path, include_user and include_transcripts explain defaults and the cost trade-off, and max_findings specifies 'most severe first' ordering. Every parameter gains meaning absent from the bare 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?

States a specific verb and resource: 'Audit AI agent and MCP client configuration files for hardcoded secrets'. The scope (client configs plus agent instruction files, project and user level) clearly separates it from siblings like scan_file, scan_directory, and scan_text.

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?

Gives clear context on the files it targets (`.mcp.json`, `.claude/settings*.json`, `.cursorrules`, user-level configs for named clients) and the defaults that shape a run (include_user=true, include_transcripts=false and 'slower'). It never states explicit exclusions or names a sibling alternative such as scan_directory, so routing is implied rather than spelled out.

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 readOnly/idempotent/non-destructive, and the description adds substantive behavior on top: git-derived file enumeration honoring .gitignore, an explicit skip list (.git, node_modules, venvs, caches, dist, build, minified bundles, lockfiles, binaries, >5 MB, .secret-sentinel.toml exclusions). It also discloses truncation semantics and ordering of findings, which an agent cannot infer from annotations alone.

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?

Front-loaded with the core purpose, then a well-structured Args/Returns block. The skip-list sentence is dense but each item earns its place; only minor trimming would improve it.

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 three parameters, real filesystem traversal complexity, and an output schema that already defines the report shape, the description covers everything an agent needs: scope, ignore/skip rules, git awareness, truncation limits, and finding-path conventions. Nothing material is missing.

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 carry the parameter burden and it does: path is documented as an absolute directory path, max_files as a stop-after cap with default 500, and max_findings as a list cap with default 200 where 0 means unlimited and results are most-severe-first. This meaningfully exceeds the bare typed 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?

Opens with a specific verb+resource+scope: 'Recursively scan a directory tree for exposed secrets.' This clearly separates it from siblings like scan_file, scan_text, scan_git_staged, and list_patterns, which an agent can distinguish without opening any 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 scope ('recursively ... directory tree', git-aware file listing) makes the intended use case obvious and implicitly routes file/text/git-index scanning to siblings. However, it never explicitly names an alternative or states when not to use it, so it stops short of full routing 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 discloses several behaviors beyond what the annotations declare. It states that UTF-8, UTF-16 and UTF-32 text is decoded by its byte-order mark, that binary files and files larger than 5 MB are skipped and reported in the summary, that the .secret-sentinel.toml and baseline settings apply, and that the tool returns an error when the file does not exist. Because the annotations already cover the read-only and idempotent safety profile, this level of added detail is strong.

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 front-loaded with a one-line summary followed by clearly labelled Args and Returns sections, and every sentence carries information. The Returns section slightly duplicates what the output schema already provides, but the pointer to scan_text for the report format is still useful.

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 two-parameter read-only scanner, the description covers encoding handling, size and binary skip rules, project-config influence, error conditions, and result ordering, which is everything an agent needs in order to call it correctly. An output schema exists, so the brief note about the redacted report is sufficient.

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 has to carry the full burden, and it documents both parameters: path as an absolute path, and max_findings with its default of 200, its 0 = no limit semantics, and the ordering (most severe first). This adds meaning the bare schema cannot convey.

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 a precise verb+resource statement, "Scan a single file for exposed secrets," which tells an agent exactly what this tool does and implicitly separates it from the sibling tools scan_directory and scan_text: it handles exactly one file. The scope of "single file" is narrow enough that the description disambiguates this tool from the directory and text siblings without opening either 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 phrase "single file" and the error behavior when the file does not exist show the intended usage context, but the description never explicitly says when to prefer this tool over scan_directory or scan_text, nor does it state any prerequisites. The implied scope is enough to infer the correct choice, but there is no explicit routing rule.

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 this a read-only, idempotent, non-destructive, closed-world operation, so the safety bar is low. The description still adds real behavioral value beyond them: findings carry the short commit hash, and a secret deleted in a later commit is still reported because history retains it, which tells the agent that results imply mandatory rotation rather than a false positive.

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?

Purpose is front-loaded in the first line, followed by the most decision-relevant caveat (deleted secrets are still reported), then parameters and returns. The structure is clean and every section earns its space; the Returns block is slightly redundant given an output schema exists, though it does flag the added commit field.

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 four parameters at 0% schema coverage and an output schema present, the description covers everything needed to invoke the tool correctly, including defaults and the 0-means-unlimited edge case. The one gap is routing: with eight siblings including two other git scanners, it never states how results or scope differ from scan_git_range or scan_git_staged.

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 carry all four parameters — and it does, documenting repo_path as an absolute path (or any path inside one), max_commits' default of 50, all_branches' inclusion of branches/tags/stash versus HEAD-only, and max_findings' default 200 with the non-obvious '0 = no limit' and severity ordering.

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 opening line gives a concrete verb and resource (scan the lines added by recent commits, git log -p), which is unambiguous on its own. It does not, however, name or contrast itself with the obvious siblings scan_git_staged and scan_git_range, leaving the boundary between those three git scanners to inference.

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?

Usage is only implied: the description explains what history scope is scanned but never states when to prefer this over scan_git_range (a specific commit span) or scan_git_staged. The all_branches note hints at the scope trade-off, but no explicit when/when-not guidance or alternative is offered.

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 readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description adds real value beyond that with default range resolution (@{upstream}..HEAD), the error behavior when no upstream exists, and finding ordering ('most severe first'). It does not mention scan cost or performance on large ranges, which is the main remaining unknown for a read-only scan.

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 lead sentence is front-loaded and high-signal, and the Args entries are tight. The Returns block is somewhat redundant given an output schema exists, and the docstring-style layout adds length without adding selection value.

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 5-parameter read-only git scanner with an output schema, everything an agent needs to invoke it correctly is present: what the range means, defaults, the upstream failure path, limits, and result ordering. No material gaps remain.

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 carry the load and it does: the Args block defines each parameter's meaning, defaults, and edge semantics ('0 = no limit', base excludes reachable commits, head is the last commit included, repo_path may be any path inside a repo). This is materially more than the bare titles/defaults in 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 first sentence gives a precise verb+resource and defines the range semantics ('Scan the commits in base..head'), with the default identified as 'what `git push` would send'. This clearly separates it from scan_git_history (all history) and scan_git_staged (index-only) without needing the 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?

'Run this before pushing' gives an explicit trigger condition, and the description explains the no-upstream failure mode plus the workaround (pass the branch you will push to as base, e.g. "origin/main"). It stops short of naming sibling alternatives such as scan_git_staged or scan_git_history when the pre-push range is not the right scope.

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?

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), it discloses that local diff settings — external diff tools, textconv filters, prefixes, path quoting — are overridden and that git runs no configured programs, which is meaningful safety context for a scanner executing inside a repo. It also explains the empty-staging behavior (clean result with explanatory summary), which annotations cannot convey.

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?

Front-loaded with the single most important constraint ('Scan ONLY the lines currently staged'), then structured Args/Returns sections. Slightly verbose in the diff-override sentence, but every clause adds real behavioral information given the empty schema descriptions.

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 2-parameter read-only scanner with an output schema, everything needed is present: scope, path semantics, result capping, edge-case behavior, and the internal git invocation guarantees. No gap an agent would need to guess at.

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 carry the load — and it does: repo_path is defined as an absolute path to a repo or any path inside one, and max_findings is explained as severity-ordered truncation with default 200 and the non-obvious semantics that 0 means no limit (a detail absent from 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?

States a specific verb (scan) and a precisely bounded resource: only lines currently staged, i.e. git diff --cached. The scope clause plus the explicit 'post-commit line number' detail makes it distinguishable from siblings like scan_git_history, scan_git_range, and scan_file.

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?

Frames the tool as 'the pre-commit checkpoint' and states that it inspects exactly what the next commit would publish, which gives an agent a clear when-to-use condition. It does not explicitly name the alternative tools (e.g. scan_git_range for unpushed commits) or state when not to use it, so it falls short of a 5.

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?

Beyond the annotations, the description discloses important behavior: placeholder handling, suppression-comment semantics, redaction guarantees, and max_findings truncation effects including added result fields. This is substantial operational context that helps an agent invoke and interpret the tool correctly.

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 purpose is front-loaded, but the long enumeration of dozens of provider and service detectors is verbose for a tool description. That list is informative but not essential for correct invocation, and it makes the definition less concise than 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?

Given the tool's complexity, the description is complete: it covers what is scanned, how findings are suppressed, how redaction works, parameter behavior, and expected return fields. The presence of an output schema reduces the burden, but the added behavioral detail makes the definition self-sufficient.

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 fully compensates by documenting all three parameters: text as raw input, source_name as the finding label, and max_findings with its default, cap behavior, and special 0 value. It also explains the extra result fields produced when truncation occurs.

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 a specific verb and resource: 'Scan a snippet of text or code for exposed secrets.' It clearly distinguishes this tool from file/directory/git scanners by emphasizing raw text snippets, so an agent can tell what it does without opening the 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 gives clear usage context by naming raw text inputs such as code, config, diff output, and logs, and by marking the tool as snippet-oriented. It does not explicitly name sibling alternatives like scan_file or redact_text, so it lacks full when-to-use/when-not-to-use routing guidance.

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