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

The annotations already declare readOnlyHint and idempotentHint, covering the safety profile. The description adds the fact that Bandit is the underlying scanner but does not disclose additional behavioral traits such as severity reporting, exit behavior, or how results are returned. 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?

The description is a single sentence of eleven words, with no filler or redundant content. It is front-loaded with the key action 'Scan' and remains appropriately sized for the tool's simplicity.

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 output schema and annotations cover return values and safety, which helps, but the description omits essential parameter semantics such as the meaning of changed_only and the default behavior when paths is null. An agent cannot confidently choose and populate the arguments without additional inference.

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%, and the description never mentions either parameter, paths or changed_only. The description must compensate for the lack of schema documentation but entirely fails to explain what these parameters mean or how they affect the scan.

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 the specific verb 'Scan' with the resource 'Python code' and the outcome 'common security problems', and names Bandit, making the core function clear. However, it does not explicitly differentiate this from sibling tools like ruff_check or ty_check, so it falls short of a 5.

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 'common security problems' implies the scanning use case and suggests this tool is appropriate when a Python security review is needed. There is no explicit statement of when to prefer Bandit over alternatives or when not to use it, so the guidance is only implied.

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, covering the safety profile. The description adds only the word 'likely', which hints that results are heuristic suggestions rather than definitive errors. It provides no additional behavioral detail such as scope limitations or what happens with changed_only, but it does not contradict annotations.

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. Every word contributes to conveying the tool's purpose, and the description is appropriately sized for a simple read-only checker.

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, has an output schema, and has safety covered by annotations, so the description does not need to explain return values or mutation risks. However, it leaves the changed_only parameter and the exact meaning of 'project text and source files' undefined, which is a clear but not severe 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 0%, so the description carries the burden of explaining parameters, but it mentions neither 'paths' nor 'changed_only'. The phrase 'project text and source files' gives some loose context for the default path scope, but it does not clarify how to restrict paths or what changed_only means.

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 ('Find') and resource ('likely spelling mistakes in project text and source files'), making the tool's function immediately clear. It is naturally differentiated from all sibling tools, which cover linting, formatting, type checking, security, dependencies, and tests rather than spelling.

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 implied rather than stated explicitly: an agent can infer to use this tool when spelling mistakes are the concern, especially since no sibling tool covers spelling. However, the description gives no explicit when-to-use guidance, exclusions, or alternatives, so it stops at the implied level.

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, covering the safety profile. The description adds useful detail about the kinds of dependency problems detected, but it does not disclose operational behavior such as whether it scans manifests, lockfiles, or the current environment. Given the strong annotations, this is acceptable but not exceptional.

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 with no filler, tautology, or repetition of schema or annotation details. Every word adds meaning.

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's core purpose is clear and the output schema plus read-only annotations help, but the complete opacity of the parameters is a significant gap. An agent can call it with defaults confidently, but cannot correctly use path scoping or the changed_only option without guessing.

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% for the two parameters, and the description provides no explanation of 'paths' or 'changed_only'. An agent has no basis for understanding what values to pass, what paths should point to, or how the 'changed_only' flag alters behavior.

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 ('Find') and identifies four distinct dependency issue categories (missing, unused, obsolete, misplaced), making the tool's purpose immediately clear. It is easily distinguished from sibling tools like ruff_check, ty_check, and bandit_check, which cover different domains.

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 for scanning dependencies for the listed issue types, but it provides no explicit guidance on when to prefer it over alternatives or when not to use it. There is no mention of how it relates to sibling tools such as ruff_check or vulture_check.

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, so the read-only nature is covered. However, the description adds no behavioral context beyond the purpose—no mention of output format, what happens when checks fail, or any configuration effects. It relies entirely on annotations, which cover safety but not operational details.

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 sentence that gets straight to the point. No fluff, no repetition, and the purpose is front-loaded. Perfectly sized for a simple tool.

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?

Although an output schema exists, the description omits critical context such as when to use the tool, what the returned results look like, and how parameters affect behavior. The tool is straightforward, but the lack of usage guidance and parameter semantics makes it incomplete for an agent to decide and invoke correctly.

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%, and the description provides no explanation of the 'paths' or 'changed_only' parameters. The schema itself lacks descriptions, so the agent has no clue what 'paths' refers to (file paths? directories?) or what 'changed_only' filters. With two parameters and zero semantic guidance, this is a severe 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?

The description states a specific verb ('Check') and resource ('docstrings against function signatures') with a clear tool reference ('pydoclint'). This is specific enough to distinguish it from sibling linting tools like ruff_check or ty_check, which focus on other aspects. No ambiguity about what the tool does.

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 guidance on when to use this tool versus alternatives like ruff_check or ty_check. The description only states what it does, not when it should be invoked. No conditions, exclusions, or comparisons are provided, leaving the agent to infer usage.

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 annotations already declare readOnlyHint and idempotentHint; the description adds the valuable behavioral guarantee that tests are collected but not executed. With annotations present, this level of added context is sufficient; it could additionally mention module import side effects, but that is not essential.

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 sentence, front-loaded with the action and scoped by the key non-execution detail. Every word earns its place; no filler or repetition.

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, has an output schema, and annotations cover safety, so the brief description is mostly adequate. However, it leaves the meaning and defaults of both optional parameters unexplained, which is a clear gap for an agent deciding how to invoke it correctly.

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% and the description adds no meaning for 'paths' or 'changed_only'. The property names give some clue, but 'changed_only' in particular is ambiguous and the description does not clarify how either parameter modulates collection.

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 ('collect') and resource ('pytest tests'), and adds the key scoping detail 'without executing them'. This clearly distinguishes it from test-running tools and from the sibling static-check tools.

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 'without executing them' implies the tool is for discovery/inspection rather than running tests, but it does not state when to prefer it over alternatives or name any explicit exclusions. Usage context is only implied, 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 declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds a useful behavior beyond annotations by noting the output is token-efficient, which helps an agent predict output size, but it does not describe return format, exit behavior, or what happens with empty paths.

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 with no filler. Every word earns its place: the verb, the tool-specific action, and the differentiating output characteristic.

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 tool with two optional parameters, full schema coverage, read-only/idempotent annotations, and an output schema, the description is sufficient for an agent to understand and invoke it correctly. The missing usage routing is covered by the usage_guidelines dimension, not by this one.

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 both parameters: paths includes glob support and the empty-means-whole-project behavior, and changed_only explains git filtering. The tool description adds no additional parameter-level detail, 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?

The description states a specific verb and resource ('Run ruff linting') and distinguishes it from the sibling ruff_format by placing the focus on linting rather than formatting. Although other check tools exist, naming the linter and action makes the purpose unambiguous.

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 guidance is given about when to choose ruff_check over siblings like ruff_format, ty_check, vulture_check, or bandit_check. The only implicit clue is 'token-efficient output,' which hints that this tool is preferred when compact output matters, but this is not stated directly and no exclusions or alternatives are named.

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, so the safety profile is known. The description's 'without modifying files' essentially repeats the read-only annotation and adds no new behavioral context like return behavior, prerequisites, or edge cases.

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 concise sentence with no wasted words. It is efficient and front-loaded with the core purpose, though it sacrifices substantive content for brevity.

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 two optional parameters and an output schema, the description should provide enough context to call the tool correctly. It only states the purpose, leaving parameter semantics, distinguishing features, and usage scenarios unexplained. It is minimally adequate but far from 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?

Schema description coverage is 0%, and the description does not mention either parameter ('paths' or 'changed_only'). The agent receives no explanation of what these parameters mean or how to use them beyond their names and types, which is insufficient.

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 action ('Check Ruff formatting') and a key trait ('without modifying files'), which is clear and not a tautology. However, it does not explicitly differentiate from sibling tools like ruff_check, so it lacks explicit distinction from alternatives.

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 provides no guidance on when to use this tool versus others, no exclusions, and no context about preferred scenarios. It is a single statement with no usage direction.

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, so the tool's safety profile is covered. The description adds the behavioral detail of an optional severity filter, but it does not disclose what `paths` or `changed_only` actually do during a check. There is no contradiction with the annotations.

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 with no filler. It states the action, resource, and the key filtering option efficiently, earning every word.

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 annotations covering safety and an output schema present, the description doesn't need to explain return values. A default invocation is clear, but the lack of parameter semantics and usage guidance makes advanced use cases like `changed_only` or specific `paths` underspecified. It is adequate for a simple tool but has clear gaps.

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 needed to compensate by explaining parameters. It only hints at the severity filter (`level`) and leaves `paths` and `changed_only` unexplained. The names and defaults are somewhat self-explanatory, but the description adds little beyond what the schema already shows.

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 clear verb ('Run') and names the specific resource ('ty type checking'), which distinguishes it from sibling tools like ruff_check and bandit_check. The mention of an optional severity filter also foreshadows the `level` parameter. It is clear and specific, though it doesn't explicitly contrast with any sibling.

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 that this tool should be used when ty type checking is needed, but it gives no explicit when-to-use or when-not-to-use guidance. No alternatives or exclusions are mentioned, so an agent must infer the usage context from the tool name and description alone.

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 annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to restate that the operation is safe or repeatable. The description adds the Vulture identity but does not disclose additional behavioral traits such as scope limits or output behavior, which leaves it adequate but not enriched.

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 with no filler or redundancy. It uses every word to convey the tool's core purpose and mechanism.

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, read-only, idempotent, and has an output schema, which reduces some burden on the description. However, the complete lack of parameter guidance leaves an agent guessing about how to specify paths and what changed_only=true actually controls, making the definition only minimally 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?

Schema description coverage is 0%, and the description does not explain the 'paths' or 'changed_only' parameters at all. The agent must infer their meaning entirely from parameter names, with no supporting detail about accepted path types or what 'changed' refers to.

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 ('Find') and the resource ('unused Python code'), and it names Vulture's dead-code analysis as the mechanism. It is distinct in function from sibling tools like ruff_check, ty_check, and bandit_check, though it does not explicitly contrast 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?

Usage is implied: an agent should call this when unused Python code needs to be detected. However, there is no explicit guidance about when to prefer this over sibling tools or any exclusion conditions, so the guidance is only implicit.

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