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

There are no annotations, so the description carries the behavioral burden. It does disclose that the tool returns a summary of what succeeded, implying partial failures are possible. However, it does not mention overwrite behavior, directory creation, or what happens with unsupported files, which would be useful for a write operation.

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 deliver the core behavior and usage condition with no filler. The key distinguishing fact (batch conversion) is front-loaded, and every word earns its place.

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 two-parameter tool with fully described schema and no nested objects or output schema, the description is largely sufficient. It covers what the tool does, when to use it, and the nature of the return value, although details like output naming or conflict handling are absent.

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 both parameters ('paths' and 'output_directory') are already well documented. The description adds little parameter-level meaning beyond the schema, which is acceptable because the schema does the heavy lifting.

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 ('convert'), a resource scope ('several documents at once'), and an outcome (returns a summary of what succeeded). It also distinguishes itself from the single-file sibling tool by explicitly framing this as the batch variant.

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 an explicit trigger: use when the user points at a set of files rather than one. It provides a clear when-to-use signal and implicitly excludes single-file use, though it does not name the alternative tool directly.

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 behavioral disclosure burden. It reveals local processing, privacy caveats for image/audio OCR modes, automatic saving beside the original, overwrite behavior with numbered fallback, and the short-vs-long return behavior—all beyond what a name alone would imply.

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 information-dense but well organized: formats first, then processing behavior, then save and return behavior. It is longer than strictly minimal, but every sentence adds a useful operational detail, so the length is justified.

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 6-parameter tool with no annotations and no output schema, the description is remarkably complete. It covers supported formats, privacy, save location, overwrite behavior, return modes, and OCR options, leaving no essential operational gap for an agent deciding whether and how to invoke the 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?

Although the schema already documents all parameters at 100% coverage, the description adds meaningful practical context: the default save behavior, privacy implications of ocr_mode, token-cost warnings for return_content 'full', and the auto-preview behavior. This helps an agent choose parameter values based on user intent rather than just type constraints.

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 and resource: converting a document to clean Markdown, and enumerates all supported formats. It clearly identifies this as a single-file conversion tool, distinguishing it from convert_folder_to_markdown and list_supported_formats by scope and purpose.

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 explicitly says to prefer this over reading a binary file directly, and gives concrete guidance on when to use return_content values such as 'full' for long documents. It also explains the default save behavior so the agent knows when not to ask the user for confirmation.

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?

No annotations are provided, so the description carries the full burden of explaining behavior. It discloses that the tool lists extensions and reports optional cloud feature configuration; both are non-mutating observational behaviors. While 'read-only' is not stated verbatim, the wording and zero-parameter schema make the tool's safe, informational nature clear.

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 with no filler: the first states the tool's primary output and the second gives the practical invocation context. The information is front-loaded and every sentence earns its place.

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 no-parameter, no-annotation introspection tool, this is almost complete: it explains what is returned conceptually and when to use it. The only minor gap is that the exact shape of the response is unspecified, but no output schema exists and the tool's simplicity makes that a small omission.

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 are zero parameters, so there is nothing for the description to clarify beyond what the schema shows. The baseline of 4 applies because parameter semantics are not a concern for this tool.

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 names a specific verb and resource: 'List the file extensions this server can convert' and also reports configured cloud features. This clearly differentiates it from sibling conversion tools like convert_to_markdown or save_summary, which perform transformations or persistence rather than introspection.

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 an explicit trigger condition: 'Call this if a conversion fails as unsupported.' This gives clear context for when to use the tool, though it does not enumerate when not to use it or explicitly contrast it with alternatives.

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 it clearly discloses the file-writing side effect, the sidecar location, and the requirement to pass real generated text. It does not mention overwrite behavior or return value, but the core behavioral traits are explicit.

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?

Every sentence carries weight: the action, the when-to-use rule, and the don'ts are all stated without repetition or filler. The structure is front-loaded with the core purpose.

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 side-effect tool with no output schema, the description covers when to use it, what to pass, and what not to do. It could add a note on overwriting an existing .md, but nothing critical is missing for correct invocation.

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, but the description adds meaning by requiring the summary parameter to be the text actually produced and clarifying that source_path refers to the converted document. This goes beyond the schema's field 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?

States a specific action (save a summary), a precise resource (as a .md file beside the document), and clear conditions. It is obviously distinct from sibling conversion tools, so an agent can select it without ambiguity.

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?

Explicitly says to call it proactively whenever summarising, outlining, or answering a broad question about a converted document, and lists exclusions (narrow factual lookups) and a prohibition on inventing summaries. This is unambiguous routing guidance.

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