ctx

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It states it returns full text and works by path, which conveys the basic behavior, but it does not mention error handling, binary file behavior, or access/auth considerations. This is adequate but lacks richer 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 a single, front-loaded sentence that states the primary behavior and provides a usage hint. Every word earns its place, with 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?

For a simple single-file retrieval tool with no output schema, the description covers the essential purpose and usage flow. It could add details about failure modes or response format, but given the low complexity and complete parameter schema, it is nearly 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?

The input schema already provides complete descriptions for all three parameters (repo, path, ref) with 100% coverage. The description adds no extra parameter-level nuance beyond what the schema states, so it is at the baseline for schema-heavy cases.

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 'Return the full text of a single file in a repository, by path' uses a specific verb and resource, clearly distinguishing this from sibling tools like list_files (listing) and search_context (searching). It makes the tool's core function immediately understandable.

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?

'Use after list_files or search_context to drill in' provides clear sequential context for when to invoke this tool. It does not explicitly state when not to use it or mention alternatives for other cases, but the usage context is unmistakable.

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 burden. It discloses the filtering behavior (stripping binaries, lockfiles, build dirs) and notes it's 'cheap' (performance). It doesn't explicitly say it's read-only, but that's implied. This adds value beyond the schema.

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: the first states the core function and key behavior, the second adds usage context. Every word earns its place, and the main verb 'List' is front-loaded.

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 has no output schema, but the description mentions 'with their byte sizes' to indicate the return shape. It also gives usage context (before packing). Could be more explicit about the exact response format, but it's complete enough for a simple listing 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 100%, so baseline is 3. The description doesn't add parameter-specific details beyond the schema, but it does contextualize why filtering happens (inclusion/exclusion) indirectly. No additional semantics 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?

The description clearly states the tool's function: 'List the text files ctx would include for a repository' with specifics like stripping binaries/lockfiles/build dirs. This distinguishes it from siblings like get_file (single file) and pack_repo (packing), making it a distinct listing/preview tool.

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?

Provides clear context: 'Cheap way for an agent to see the layout before packing.' This tells the agent when to use it (before packing), but it doesn't explicitly mention alternatives or exclusions. Still, the context is strong enough for selection.

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 and does well: it discloses that pages are extracted to clean Markdown, concatenated with URLs, stays within the same site section, and is bounded by depth and page count. It doesn't mention potential edge cases or side effects, but covers the core behavior thoroughly.

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 dense sentences, front-loaded with verb+resource and output format. Every sentence adds value: what it does, how it behaves, and how to control it. No fluff 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?

Despite having no annotations or output schema, the description covers the tool's purpose, output format, constraints, and budget control. It gives an agent enough information to select and invoke the tool correctly, making it complete for the tool's 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 coverage is 100% for all 4 parameters, so the baseline is 3. The description reinforces the roles of depth/page count ('bounded by depth and page count') and max_tokens ('Use max_tokens to fit a budget'), but doesn't add new details beyond the schema, so it earns the baseline score.

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 ('Crawl') and resource ('documentation site'), clearly stating the output ('one agent-ready context blob' of Markdown). It distinguishes itself from siblings like pack_repo (which packs code repositories) and search_docs (which searches, not crawls).

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 when to use it ('Crawl a documentation site from a start URL'), and clarifies constraints like staying within the section and being bounded by depth/page count. However, it does not explicitly mention when not to use it or name alternative tools, so guidance is 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.

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

With no annotations, the description carries full behavioral burden. It discloses the output format (headers, stripping of binaries/lockfiles/build dirs), token estimate presence, and filtering behavior. This is substantial, though it omits edge cases like size limits or error handling.

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 two sentences, front-loaded with the core purpose followed by behavioral details. Every phrase earns its place—no redundancy or 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?

The description accurately conveys the return format (context blob with headers, token estimate) and major options. With no output schema, this is sufficient. It lacks some depth on limitations (e.g., max repo size, include/exclude precedence), but the core usage is well covered.

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 the baseline is 3. The description adds practical value by explaining the purpose of include/exclude and max_tokens (focusing the repo and fitting a budget), which goes beyond the schema's property descriptions.

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 tool fetches a GitHub repository and returns it as a concatenated text blob with headers, stripped binaries/lockfiles/build dirs, and a token estimate. This specific verb+resource+output format distinguishes it from siblings like get_file and list_files.

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 (whole-repo aggregation with optional include/exclude filtering) and gives usage tips for globs and max_tokens, but it does not explicitly state when to prefer this tool over siblings or when not to use it. No alternative tools are mentioned.

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 burden of disclosing behavior. It does so by explaining that only matching passages are returned, with specific metadata (file path, line number, relevance score), and that it is token-efficient. This goes beyond a bare name and offers useful behavioral context, though it doesn't mention permissions or potential side effects (which are likely nonexistent).

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 two sentences, front-loaded with the core action and output, and includes a practical usage tip. Every sentence earns its place without fluff.

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 7 parameters and no output schema, the description does a good job of explaining the overall purpose and return shape. It doesn't explain all parameter interactions, but the schema descriptions handle those. It lacks details on error conditions or edge cases, but for typical use it 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 100%, so the baseline is 3. The description does not add any extra meaning about parameters beyond what the schema already provides. The term 'query' is referenced, but not elaborated beyond the schema's own description.

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 tool's verb plus resource: 'Search a GitHub repository and return only the passages that match a query.' It specifies the output format (file path, line number, relevance score), and differentiates itself from the sibling tool pack_repo by highlighting token efficiency for targeted searches.

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 explicit guidance on when to use this tool over pack_repo ('when you need a specific detail'), and contrasts it with the more heavy-weight pack_repo. It doesn't explicitly mention other siblings like search_docs, but the stated use case is clear enough to guide selection.

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?

Given no annotations, the description carries the full burden. It discloses the crawling behavior, that it returns only matching passages, and the output fields (URL, line, relevance score). It also adds the token-efficiency context. However, it doesn't explicitly state that this is a read-only operation or mention rate limits or error conditions, which would be useful given no 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?

Two sentences, no filler. Front-loaded with the core function and output, then a use-case justification.

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 adequately covers the tool's purpose, output format, and use case. It lacks an explicit note about potential network latency or lack of results, but the schema covers all parameter constraints. Given no output schema, the description's outline of return fields 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?

All 6 parameters are fully described in the schema (100% coverage), so the description doesn't need to add parameter details. The description itself doesn't add any extra parameter semantics beyond what the schema provides, 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?

The description uses a specific verb ('Crawl') and resource ('documentation site'), and specifies the exact return content (passages with page URL, line, relevance score). This clearly distinguishes it from sibling tools like pack_docs or get_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?

It provides clear context for when to use: to answer a question from docs without packing the whole site. However, it does not explicitly mention when not to use or name specific alternatives like pack_docs or search_context.

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