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

With no annotations, the description carries the full burden of behavioral disclosure, but it only states the output. It does not mention sorting direction, recursion behavior, handling of hidden files, file size calculation details, or whether the operation is read-only. The phrase 'Top file extensions by total size' implies some aggregation behavior but provides no explicit behavioral context.

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 extremely concise and front-loaded, with no filler words or redundant content. However, it may be too sparse for a tool with six parameters and no annotations, so while it earns high marks for conciseness, it is not the ideal size for the tool's complexity.

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 description is severely incomplete for a tool with six parameters, no output schema, and no annotations. It gives no usage guidance, behavioral details, or parameter semantics, leaving the agent to guess how to invoke it correctly. This is a one-line description for a non-trivial 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?

Schema description coverage is 0%, so the description must compensate for six undocumented parameters. It adds no direct explanation of rootPath, limit, maxDepth, maxFiles, ignoreGlobs, or includeGlobs. The word 'Top' loosely hints at the limit parameter, but this is not sufficient for the agent to determine how to set parameters correctly.

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 identifies the resource (file extensions) and the metric (total size), and the word 'Top' implies a ranked result. It distinguishes from sibling tools like top_dirs and top_files by focusing on file extensions, but lacks an explicit verb such as 'List' or 'Compute'.

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 alternatives such as scan_summary, top_dirs, or top_files. It does not mention any use cases, prerequisites, or exclusions, so an agent has no context for selecting it.

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 '(read-only)' annotation in the text is a useful behavioral disclosure given no annotations are present. However, it does not mention recursion behavior, resource-intensive hashing, or any caveats about limits, leaving much of the behavior unspecified.

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 with no redundant words, making it highly concise. However, it is so brief that it under-specifies, as conciseness should not come at the expense of necessary detail.

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 tool with six parameters and no output schema, the description is too sparse. It provides only a high-level definition and omits usage context, parameter semantics, and expected return behavior, making it incomplete for effective use.

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 and no parameter explanations in the description, the meaning of all six parameters (rootPath, limit, maxDepth, etc.) is left entirely to the schema property names. The description does not compensate for the coverage 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 clearly conveys that the tool identifies groups of files that share identical size and content hash, which distinguishes it from sibling tools like stale_candidates. However, it lacks an explicit verb (e.g., 'Finds' or 'Returns'), reducing specificity.

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 guidance is provided on when to use this tool versus alternatives. The description does not mention scenarios, prerequisites, or conditions that would favor duplicate_candidates over other sibling tools.

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 explicitly notes 'read-only', a key behavioral trait absent from annotations. However, it does not disclose other behaviors such as handling of symlinks, the maxFiles limit, or potential performance implications. With no annotations, the description carries the burden but only partially fulfills it.

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, well-front-loaded sentence. It states the core purpose and two key features without redundancy. Every word contributes 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?

With 6 parameters and no output schema, the description covers the core behavior but omits important constraints like maxFiles limit, symlink handling, and the nature of the report. It does not explain how the summary is returned or any resource limitations, leaving the agent with partial contextual understanding.

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 83%, so the baseline is 3. The description mentions 'ignore globs and depth limits', aligning with ignoreGlobs and maxDepth, but adds nothing beyond the schema's existing parameter descriptions. The rootPath parameter lacks a schema description, but the description implies it via 'Scan a directory'.

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 (scan), resource (directory), and outcome (summarize total size, files, dirs). It distinguishes this tool from siblings like top_dirs or top_files by emphasizing a general summary rather than specific rankings.

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 obtaining directory statistics but does not explicitly state when to prefer this tool over alternatives or when not to use it. No exclusions or alternative tool references are provided, leaving the agent to infer context.

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 present, the description carries the full burden of behavioral disclosure. It states 'read-only suggestions,' implying non-destructiveness, but does not explain selection criteria, output format, or any side effects. This is insufficient for a tool with no metadata to rely on.

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 extremely short, but this is under-specification rather than conciseness. The single phrase does not provide enough information to be actionable, so it does not earn its place in the tool definition.

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 (8 parameters, no output schema, no annotations), the description is expected to explain behavior and usage. It only offers a vague label, making it completely inadequate for an agent to select and invoke the tool 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?

The input schema contains 8 parameters with 0% coverage from the description. The description does not mention rootPath, limit, minSizeMB, or any other parameters, leaving the agent to guess their semantics. This is a complete failure to compensate for the schema's lack of descriptive text.

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 'Large and old files (read-only suggestions)' uses a noun phrase rather than an imperative verb, leaving ambiguity about whether this tool scans, lists, or reports. It hints at the tool's focus but does not clearly state the action, making it hard to distinguish from sibling tools like top_files or duplicate_candidates.

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 guidance is provided on when to use this tool versus alternatives like top_files or duplicate_candidates. The 'read-only' hint is the only context, but it does not direct the agent toward a specific use case or provide exclusions.

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 provided, the description carries the full burden. It does not disclose any behavioral traits beyond the basic purpose: no mention of recursion behavior, performance implications, sorting order, or how parameters like maxDepth or maxFiles affect results. This is a significant gap for a scanning tool.

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 extremely brief (one fragment), which is not conciseness but under-specification. While it is front-loaded, it omits critical information needed for correct use. Every sentence should earn its place, but here the single sentence is insufficient.

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 has 6 parameters, no annotations, and no output schema, the description is severely incomplete. It provides no context on return format, parameter effects, potential side effects, or when to use it. This is inadequate for a tool of this complexity.

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 any parameters. It only implicitly mentions rootPath via 'under root' and file size sorting, but limit, maxDepth, maxFiles, ignoreGlobs, and includeGlobs are entirely unexplained. The description fails to compensate for the lack of schema documentation.

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 identifies the tool's purpose: finding heaviest directories by aggregate file size under a root. It distinguishes itself from sibling tool 'top_files' by focusing on directories rather than files. However, it lacks an explicit verb (e.g., 'list' or 'find'), so it is a noun phrase rather than a full sentence.

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 guidance is provided on when to use this tool versus alternatives like top_files or stale_candidates. The description only states what it does, not the context for choosing it. There are no exclusions or comparisons to sibling tools.

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 that optional filters exist for size, age, and glob patterns, which is a behavioral trait beyond the schema. However, it does not mention whether the operation is read-only, output format, sorting order, or potential performance impacts. With no annotations, more detail would be expected.

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 extraneous words. It efficiently conveys the core purpose and key filter capabilities.

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 has 9 parameters, no output schema, and no annotations, this description is incomplete. It does not explain return values, sorting order, default behavior, or practical usage context, leaving the agent with many unresolved questions.

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 must compensate for parameter explanation. It references size, age, and glob include/exclude, which maps to several parameters, but completely omits limit, maxDepth, maxFiles, and rootPath. The high-level categories help but leave significant gaps.

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 identifies the resource as files and the intent to show the largest ones, differentiating it from sibling tools like top_dirs by specifying files. However, it lacks an explicit verb such as 'list' or 'show', making the purpose slightly implicit.

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 no guidance on when to use this tool versus alternatives like top_dirs or scan_summary. It only implies usage through its filter options, but does not state prerequisites, exclusions, or alternative recommendations.

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