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

With no annotations, the description carries the full burden. 'Attempt download' implies a possible network fetch and side effect, but it never says whether a file is saved, whether this is a read-only probe, what permissions or rate limits apply, or whether failures throw versus return an error payload.

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 tight sentence, front-loaded with the verb and resource, with no filler. It is arguably too short rather than padded, which is the preferred failure mode.

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?

No annotations and no output schema, so the description must explain what 'detailed error' actually contains and what the caller gets back on success versus failure. It does neither, leaving the diagnostic result shape entirely undefined.

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 both parameters are documented in the schema, so the baseline of 3 applies. The description actually adds a small point of confusion by referring to a 'page URL' rather than the integer page plus base_url the schema defines.

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 (diagnose) and resource (a page URL), and the phrase 'attempt download and report detailed error' distinguishes it from the plain download_page sibling by stating it returns diagnostics rather than content. Misfit: it says 'page URL' while the schema actually takes a page number plus a base_url, which muddies the resource identity slightly.

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 explicit when-to-use or when-not-to-use guidance. The diagnostic intent implies it is for troubleshooting failures, but the siblings download_page and inspect_page are never named, so the agent must guess which tool to call first.

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 behavioral burden. It says 'Download' but does not explain where the file is saved, what is returned, whether authentication is needed, or what side effects occur, leaving significant gaps for a download 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?

The description is a single, front-loaded phrase with no wasted words. However, it is so terse that it provides almost no structural context, bordering on under-specification rather than effective conciseness.

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 three parameters, no annotations, and no output schema, so the description should explain return behavior and side effects. It does not cover what the download produces, where it is stored, or how failures manifest, leaving the agent with an incomplete picture.

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 schema already documents all three parameters. The description adds no syntax or meaning beyond the schema, making the baseline score of 3 appropriate.

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 ('Download') and resource ('a single page'), and the word 'single' distinguishes it from the sibling download_range. It does not name the sibling or clarify how it differs from inspect_page, but the core purpose is clear.

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 explicit guidance on when to use this tool versus download_range or inspect_page, and no prerequisites or exclusions are stated. The only implied usage is that it handles one page instead of a range.

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 behavioral burden, yet it discloses nothing about what 'download' produces (files on disk, returned bytes, URLs), whether partial failures are tolerated, or any auth/rate-limit constraints. The only implied behavior is that it operates on multiple pages at once.

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 four-word sentence with no filler, but it is under-specified rather than efficient. Front-loading is fine; there simply isn't enough content for the agent to act on.

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 four parameters, three of them required, no annotations and no output schema, the description should at minimum explain what a 'download' yields and whether book is mandatory. Everything an agent needs beyond the page bounds and base URL is missing. The complete schema coverage of the surfaces it does touch keeps this from falling lower.

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 start, end, book and base_url are each documented in the schema, and the description's 'range of pages' only loosely echoes the inclusive start/end semantics already stated. Baseline 3 applies since 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 verb+resource pair ('Download a range of pages') is concrete, but the description never distinguishes it from the sibling 'download_page', which an agent would naturally consider for the same resource. The word 'range' is the only hint at the difference and the agent must infer it.

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 statement of when to use this versus 'download_page' or 'inspect_book'/'prepare_ocr', nor any prerequisites such as whether a book identifier is needed. Usage must be fully inferred from the tool name.

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 exist, so the description carries the full burden. 'Inspect' and 'verify' imply a non-mutating operation, and it discloses the two things it produces (accessibility status, sample page info), but it says nothing about failure modes (unreachable URL, invalid book id), rate limits, or auth requirements.

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 naming the resource then the two outputs, with zero filler. Appropriate size for a two-parameter inspection 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?

With no output schema and no annotations, the description is the only source for return-value behavior, and 'sample page info' is left undefined. For a simple read-only check this is minimally viable, but an agent cannot predict the response shape or error signaling.

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% with only two params, both documented in the schema itself. The description adds no format hints (e.g., how a book identifier is formed vs. base_url), 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?

Specific verb ('Inspect') plus resource ('a Matricula book'), with the two concrete outcomes named: accessibility verification and sample page info. This clearly separates it from download_page/download_range siblings, though it never names an alternative explicitly.

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 'verify accessibility' implies a pre-flight check before downloading, but the description never states when to call this versus inspect_page or download_page. Usage is inferable rather than declared.

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 full behavioral burden and does almost none of it. It says nothing about authentication, network access to the Matricula viewer, failure modes, or whether anything is cached or written to disk by 'download'. Only the minimal 'it downloads and inspects' is conveyed.

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 short sentence with no filler, and the core action is front-loaded. Its brevity is a liability for other dimensions but there is no structural waste to penalize.

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 no annotations and no output schema, the description needs to explain what a caller gets back from inspecting a page and how errors surface. It omits return values, output destination, and relationship to the sibling tools entirely, leaving significant gaps for a two-required-parameter network operation.

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 all three parameters (book, page, base_url) are already documented by the schema, making 3 the baseline. The description adds nothing about parameter behavior, such as whether `book` is optional, how `page` interacts with `book`, or what form `base_url` takes.

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 gives a verb-plus-resource ('Download and inspect a single page'), so the basic action is understandable. However, it does not distinguish this from the sibling `download_page`, which sounds like it also downloads a single page, nor does it clarify what 'inspect' adds. An agent cannot confidently choose between these two 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?

No guidance on when to use this tool versus `download_page`, `download_range`, or `inspect_book`. The word 'inspect' weakly implies a verification/diagnostic role, but the description never states a selection condition or prerequisite.

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, and it does useful work by resolving the ambiguity of the name 'prepare_ocr' — clarifying that the tool lists files and sizes rather than mutating or converting anything. However, it never states whether any files are written, whether this is read-only, what permissions are needed, or how large directories are handled, which are real gaps for a tool whose name implies a write/prep step.

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: the action comes first and the concrete behavior ('list files and sizes') follows after the colon. It is efficient, though so terse that it borders on under-specification rather than true conciseness.

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?

Both parameters are documented and 'list files and sizes' effectively describes the return shape, which compensates for the absent output schema. What is missing is the behavioral contract an agent needs before invoking: whether anything is created or modified, and how this fits into the sibling workflow.

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% ('Book identifier', 'Directory containing images'), so the schema already documents both parameters. The description adds no extra semantics such as path format, defaults for the optional book/directory, or what happens when they are omitted; 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 concrete verb ('prepare ... for OCR') and resource ('a directory of images'), plus the concrete action of listing files and sizes. It does not differentiate itself from any sibling such as verify_image or inspect_page, so an agent must infer the boundary, but the purpose itself is 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?

There is no statement of when to choose this over verify_image, inspect_page, or diagnose_error, and no mention of prerequisites such as whether an OCR pipeline must exist or whether files need to be downloaded first. The only guidance is the implicit hint in the phrase 'for OCR'.

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 behavioral burden and does not meet it. It never says what happens on failure (exception vs. boolean), whether it reads only headers or fully decodes the file, or whether it requires the file to already exist on disk.

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 padding or redundancy. Every word (verify, downloaded, JPEG) 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?

For a one-parameter check with no output schema, the description should state the success/failure signal so an agent knows whether to branch on a return value or catch an error. That, plus the JPEG-only scope question, is the remaining gap; otherwise the tool is simple enough that little more is needed.

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?

One parameter with 100% schema description coverage, so the schema already documents the path argument. The description adds only the implication that the path points at a previously downloaded image, no format or validation detail beyond that. 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 (verify), a specific resource (downloaded image), and the concrete check performed (valid JPEG). That distinguishes it from the sibling tools, which are all page/book retrieval or OCR-prep operations. It does not say whether non-JPEG formats are in scope, keeping it 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?

"Downloaded image" implies the workflow position (a check after download_page/download_range), but there is no explicit when-to-use, when-not-to-use, or named alternative. Usage is inferable rather than stated.

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