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

With no annotations, the description carries the full transparency burden. It discloses two behavioral traits: the operation pushes, and compilation is limited to roots that reference the asset. Still, it does not mention overwrite behavior, permissions, or what 'push' entails, leaving meaningful gaps for a mutation 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 two sentences, front-loaded with the action, and every sentence adds value. The second sentence provides a useful behavioral nuance without unnecessary elaboration.

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 an output schema, the tool has four parameters, no annotations, and no parameter descriptions. The description explains the core action and one safety property, but it omits the meaning of message/project and does not clarify side effects beyond 'push.' This is incomplete for reliable 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 description coverage is 0%, so the description must compensate for the four parameters. It hints that local_path is a local file and that 'push' relates to message, but it never explicitly defines dest, message, or project. This is insufficient for an agent to confidently map inputs.

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 opens with a specific verb and resource: 'Copy a local image or binary into the project, then push.' This clearly distinguishes add_asset from siblings like write/edit (text creation) and compile/render (build operations). The additional note about compilation scoping reinforces its unique role.

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 makes the primary use case explicit: adding a local image or binary into the project. It also provides a practical safety guideline: an unreferenced file cannot break a build. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

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 provided, so description carries full burden. It discloses that errors block push while warnings do not, and verbose flag reveals all errors/warnings. However, it does not mention side effects or permissions. Given the tool's nature, this is good but not exhaustive.

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 concise sentences, front-loaded purpose, then behavioral specifics. No redundancy.

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 an output schema existsaine, the description covers error handling and return value. It lacks explanation of 'project' parameter, but overall it's sufficient for a compile tool. Complexity is moderate.

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 0%, so description must explain parameters. It explains 'verbose' but 'path' is only implied as 'root owning path' and 'project' is completely absent. With 3 parameters, this 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 phrase 'Compile the root owning `path` and return a digest' provides a specific verb (compile) and resource (root owning path). It is distinguishable from siblings like render or read, though 'root' is ambiguous without context. The purpose is clear but not fully specified.

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 mentions error behavior but does not explicitly state when to use this tool vs. alternatives or provide exclusions. It implies use when you need to compile and check for blocking errors before pushing, but no explicit comparison with siblings.

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. It reveals critical behavior: compilation and push, and automatic revert on compile failure. It could be richer (e.g., side effects, access requirements), but it goes beyond a basic edit description.

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, front-loaded key information, no fluff. 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?

Despite having an output schema, the complete lack of parameter documentation makes the tool hard to use correctly. Key behaviors like reversion and compilation are disclosed, but without parameter semantics, the description is incomplete for a 5-parameter 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% and the description provides no parameter explanations. With 5 parameters (4 required), the description should at least mention what 'old', 'new', 'path', 'project', or 'message' represent. It adds no value for parameter understanding.

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: 'Replace an exact snippet, then compile and push.' It clearly differentiates from siblings like 'write' by highlighting the 'exact snippet' matching and the auto compile/push behavior. This is a strong, specific verb+resource statement.

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 a clear usage constraint: '`old` must appear exactly once.' This implies when the tool is appropriate (exact unique snippet) without stating exclusions. It doesn't explicitly name alternatives but gives enough context for a competent agent.

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, and the description does not disclose any side effects, permissions, or failure modes. It implicitly suggests a read-only listing but never states so, leaving the agent to guess about implications like whether it modifies state or requires special access.

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, tightly worded sentence that conveys the core functionality directly. There is no redundant information, and the structure is optimally concise 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?

The description does not explain the output format or the meaning of 'roots' (e.g., in a LaTeX project hierarchy). It also omits any mention of the 'project' parameter, leaving gaps in the overall context needed 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?

The input schema has a single parameter 'project' with no description, and the tool description does not mention it at all. With 0% schema coverage, the description fails to explain what 'project' refers to or how it affects the listing, leaving the agent without essential information.

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 ('List') and the resource ('.tex files'), and adds a distinctive detail ('marking which are roots') that differentiates it from other tools like read, grep, or edit. It is unambiguous and specific.

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 does not provide any guidance on when to use this tool instead of alternatives. It merely states what it does, without contextual cues such as 'use this before compiling' or comparisons to other listing/reading 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?

With no annotations, the description carries the transparency burden. It correctly implies a read-only operation, but it says 'the project' while the schema's glob default is '*.tex', meaning the search is actually restricted to .tex files by default. This misleading scoping is not disclosed. The description also omits case-sensitivity or hidden-file behavior, though the output format is mentioned.

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 adds meaning: the operation, the target resource, and the result format.

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 existence of an output schema covers return values, so the description doesn't need to elaborate them. However, the tool is not fully complete for an agent: it lacks context about glob/project semantics and the effect of defaults. For a simple search tool, it's adequate but has clear gaps preventing a higher score.

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 add meaning for parameters. The term 'Regex-search' implies the 'pattern' parameter is a regular expression, but the 'glob' and 'project' parameters are never mentioned. The description fails to explain their purpose (file filter and project scope), leaving agents to guess from names alone.

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 'Regex-search the project, returning file:line: match' uses a specific verb ('Regex-search') and resource ('the project'), clearly distinguishing it from sibling tools like outline, files, and read. It also states the return format, making the purpose unmistakable.

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 when-to-use or alternatives are stated. However, the purpose is so transparent that an agent can infer it is the tool for regex-based search across a project. It doesn't say when not to use other tools, but the description implies its usage clearly.

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 transparency burden and does disclose substantive behaviors: pulling, verifying local package resolution, and baseline-compiling roots. However, it does not mention potential side effects of the pull/compile, permissions needed, or what happens on failure, leaving notable gaps.

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 focused sentence that front-loads the main action and then lists the required safety-gate steps. Every clause adds useful information, and there is no filler or redundant repetition of the tool name.

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 relatively low-complexity with one parameter and an output schema, so the description covers the high-level workflow well. However, it lacks parameter semantics and side-effect disclosure, and with no annotations the description must bear more weight than it currently does.

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 schema has one parameter, 'name', with a default of empty string and 0% schema description coverage. The tool description never explains what 'name' should contain (project identifier? path?), how it is used, or whether it is truly optional. This is a significant omission for a single-parameter 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 clearly identifies the action as opening a project and running a safety gate with specific steps: pull, verify \usepackage resolution, and baseline-compile each root. This distinguishes it from sibling read/write/compile tools, especially by positioning it as a prerequisite before any write.

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 explicitly states 'Required before any write,' giving a clear condition for when to use this tool rather than directly using write/edit siblings. It does not enumerate exclusions or alternative tools, but the required-before-write context is strong guidance.

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 behavioral disclosure. It implies a read-only, cheap operation and mentions line numbers, but it does not explicitly state side effects, error behavior, or how the outline is computed. This is helpful but incomplete.

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 short sentences, front-loaded with the core purpose and followed by usage guidance. Every sentence earns its place with no repetition 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?

An output schema exists, so return-value details are structurally covered. The description supplies the essential orientation: what the tool maps, that it is cheap, and when to use it. It would benefit from clarifying the 'project' parameter and supported file types, but overall it is reasonably complete for a simple overview 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%, and the description adds no explanation of the 'path' or 'project' parameters. 'Path' is inferable from the tool's purpose, but 'project' remains entirely opaque, so the description provides little parameter-level value beyond the schema titles.

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 ('Map') and resource ('a document's structure'), and enumerates what is included: sections, figures, labels, includes. It also differentiates from sibling tools like read by emphasizing line numbers and the low cost compared to reading the whole 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?

The description explicitly states when to use the tool ('Use before reading') and frames it as a cheap precursor to reading the full file. It provides clear context but does not explicitly name alternative tools or say when not to use it, so it stops short of a 5.

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 implies a read-only operation with no side effects, which is generally safe. It does not explicitly state 'read-only' but the verb 'read' is clear enough for a low-risk 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 concise, with exactly three short sentences that front-load the purpose and provide necessary guidance without extraneous details.

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?

It covers the core usage and lines parameter, but leaves the 'project' parameter unexplained and does not mention output format or any additional context. For a simple read tool, this is adequate but not fully detailed.

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 description explains the lines parameter well (e.g., 'lines=150-190 reads a range; omit for all'), but does not clarify the 'project' parameter. The path parameter is self-explanatory.

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 reads a file and mentions it is line-numbered. This distinguishes it from sibling tools like write or edit, providing a specific verb and resource.

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 guidance on using the lines parameter and suggests preferring a range guided by an outline, but does not explicitly compare with alternatives or state when to use this tool over others.

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?

There are no annotations, so the description carries the behavioral burden. It meaningfully discloses that rendering is expensive and that it is not for text extraction. However, it does not say what the returned image looks like, whether it has side effects, or what happens if the PDF is not compiled, leaving some gaps in 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?

Two sentences carry a clear purpose, an explicit limitation, a cost warning, and a pointer to an alternative tool. The most important information is front-loaded, and there is no wasted text.

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 three parameters, no annotations, and no output schema, the description is reasonably complete: it defines the input (compiled PDF → page image), the purpose (layout only), the cost profile (expensive), and the alternatives. The main missing piece is the purpose and behavior of 'project', but the description covers the essential usage decisions.

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 directly explain the parameters. It weakly implies 'page' via 'one page' and 'path' via 'compiled PDF', but it says nothing about the 'project' parameter, path resolution, or defaults. The description therefore adds minimal meaning beyond the schema's raw field names.

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 opens with a specific purpose: render one page of a compiled PDF as an image. It explicitly scopes the tool to layout checks (float placement, overlap, figure sizing), and it calls out read() for text, so the tool is clearly distinct from siblings.

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 includes explicit usage direction: try compile() warnings first, then use render() for layout issues; use read() for text. This tells the agent both when to invoke this tool and when to prefer a sibling, which is exactly what this dimension asks for.

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 behavioral disclosure. It reveals core behaviors—create, overwrite, compile, push—and warns that overwriting occurs, which is important. However, it omits details about compile/push side effects, failure modes, permissions, or reversibility, leaving significant behavioral gaps.

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 every clause contributes useful guidance. It is appropriately concise and well structured.

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 complex (write + compile + push), has four parameters with zero schema description coverage, and no annotations. The description covers purpose and key usage but fails to explain message/project semantics, compile/push behavior, or prerequisites, leaving an agent under-equipped for reliable 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 description coverage is 0%, so the description must compensate, but it adds almost no parameter-level meaning. 'Path' and 'content' are somewhat implied by 'Create or overwrite a file,' but 'message' and 'project' are left entirely unexplained. The agent cannot infer the purpose or format of these parameters from the 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 states a specific action ('Create or overwrite a file') with clear resource scope and adds side effects ('then compile and push'). It explicitly distinguishes itself from the sibling edit() tool by directing users to prefer edit for changes to an existing document.

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 usage context: 'For new documents and whole-file rewrites' and directly names the alternative tool: 'prefer edit() for changes to an existing document.' This clearly tells an agent when to select write over its closest sibling.

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