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

Annotations already establish readOnlyHint and closed-world safety, so the description only needs to add behavior beyond that. It does: it discloses that trailing commas are removed, JSON values are preserved, and cleanup details are reported, which tells an agent the transformation is lossless-ish and observable. It stops short of saying what happens on unparseable JSON.

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, front-loaded with the core action, with the input-tolerance and cleanup behavior packed into the second. No filler, no repetition of the title.

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, so return values needn't be explained; the description still usefully notes that cleanup details are reported. Inputs, tolerance for fences/prose, and the mutation-free nature of the transform are all covered, leaving only error behavior unspecified.

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 both 'payload' (fence/prose tolerance, 1MB cap) and 'indent' (0 for compact) are already fully documented in the schema. The description's note about accepting a code fence or prose restates the payload description rather than adding new semantics, so the baseline 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 and resource ('Clean up and pretty-print a JSON object or array') and immediately scopes it to JSON text with optional fences or prose. An agent can tell exactly what the tool consumes and produces 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 implies the use case (repairing/prettifying JSON that carries fences, prose, or trailing commas) but never states when to reach for this over, say, a validator or parser, nor any exclusions. Usage is inferable 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 destructiveHint=true, readOnlyHint=false and non-idempotent, and the description reinforces this with 'This tool modifies Git state' and the review-before-commit rule. It adds genuinely new behavioral detail the annotations cannot convey: the preview diff is bounded, and the commit stages ALL non-ignored changes (i.e., scope is broader than one file). It stops short of covering failure modes such as nothing-to-commit or whether a remote push happens.

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?

Three sentences, front-loaded with the call-first instruction and the safety gate last. The mode check is embedded in the same clause as its effect, so nothing is wasted or buried.

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-param, 0-required mutation tool with a full output schema, the description covers the decision the agent actually faces: preview vs commit, how to build the message, and what the commit will sweep in. Return-value format is correctly left to the output schema.

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% and the schema property descriptions already explain omitting commitMessage for a preview, the single-line Conventional Commit form, and the repositoryPath default. The description restates the mode semantics rather than adding new parameter meaning (no format examples, no note that Conventional Commit subjects can exceed the 100-char cap). Baseline 3 applies when the schema carries the load.

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 (preview/inspect and create a Git commit) and makes the two operating modes explicit: preview when commitMessage is omitted, commit when it is supplied. An agent can tell exactly what the call will do without opening the schema, and the sibling tools (docker, logs, json) are clearly unrelated.

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 an explicit ordered workflow — call first without commitMessage, generate a Conventional Commit message from the changes, call again with commitMessage — plus a gating rule ('only commit after reviewing the preview'). This is exactly the when/what-order guidance an agent needs for a two-phase mutation.

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 openWorldHint=true, so the safety profile is clear; the description adds only the default filtering behavior. It does not mention that the Docker daemon must be reachable, what happens on connection failure, or whether results are a point-in-time snapshot — meaningful context for a tool that depends on an external runtime.

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 short sentences, front-loaded with the purpose and then the default scope; nothing is wasted. Minor redundancy with the schema's default value keeps it from a 5.

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-optional-parameter read tool with an output schema and explicit readOnly annotations, the description covers purpose and default scope adequately. It stops short of explaining the daemon dependency or result semantics, but nothing an agent needs to call 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?

Schema coverage is 100% and the single parameter's description already explains that it includes stopped containers, so the schema carries the semantics. The description's "shown by default" merely restates the default value rather than adding selectivity nuance. Baseline 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?

The description states a specific verb and resource ("List local Docker containers and their current status"), which is unambiguous on its own. Sibling tools are unrelated (logs, JSON formatting, git), so no sibling differentiation is required. The only friction is the title saying "Inspect" while the description narrows scope to listing, a mild mismatch.

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?

"Running containers are shown by default" implies the condition under which includeStopped matters, but it never says when to prefer this over other ways of querying container state, nor any prerequisites. The absence of related siblings softens the gap, but guidance is implied rather than stated.

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 readOnlyHint=true and openWorldHint=false already covering safety and locality, the description goes further: it discloses that very long lines are skipped and that a 'truncated' signal marks safety/result-limit stops. That is real behavioral context an agent could not get from the annotations, though rate/permission behavior is untouched.

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, no filler, and the most important constraint (search root) comes before the edge-case behavior (skipped lines, truncation). Every clause carries information.

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, so return-shape explanation is unnecessary; the description still explains the notable 'truncated' signal. Combined with the schema's per-parameter detail, an agent has enough to call it correctly; only explicit when-to-use guidance 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 coverage is 100%, so paths, pattern, maxResults and caseSensitive are all documented in the schema itself. The description adds nothing parameter-specific beyond the concept of a regex pattern, which the schema already states, so baseline 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 and resource: 'Search local log files for a regular-expression pattern'. The scope qualifier (TOOLBOX_LOG_DIRS / cwd) narrows the resource precisely. Siblings (docker, JSON, git) are unrelated, so no explicit differentiation is needed, but the description never says it out loud.

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?

Conveys the searchable domain and the fallback to cwd, which implicitly tells an agent when the tool applies. It does not state when not to use it or name any alternative for, say, non-log content, so guidance stays 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.