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

No annotations are provided, so the description carries the full burden. 'Without inventing claims' hints at honesty but does not disclose potential side effects, permissions, or output format. It is insufficient for a tool that might read files and produce a fit assessment.

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 zero wasted words. It efficiently conveys the tool's action and a key constraint.

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 simple with 2 parameters and no output schema, but the description does not explain what the tool returns or any prerequisites (e.g., that the application must exist). It is minimally viable for comprehension but lacks completeness regarding expected outcome.

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% and the description does not explicitly explain either parameter. However, the noun phrases 'private JSON profile' and 'saved job description' give implicit clues that profile_json_path likely points to the profile and application_id identifies the job description, offering limited semantic value.

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 'Compare' and identifies the resources ('private JSON profile', 'saved job description'), clearly distinguishing it from sibling tools like create_application or render_application_drafts. The phrase 'without inventing claims' adds unique specificity about the tool's function.

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 use when a profile and a saved job description exist and a fit comparison is needed. It provides a clear context but does not explicitly mention when not to use it or name alternatives among the siblings, warranting a 4 rather than 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?

With no annotations provided, the description carries the full burden. It adds one meaningful behavioral detail ('no shell command is used'), which is a safety-relevant trait. However, it omits other aspects like output format, side effects, or error behavior, so transparency is moderate but not comprehensive.

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 conveys the core action and a key safety note without filler. Every word earns its place, making it highly 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?

There is no output schema or annotations, so the description must explain the tool's effects and returns. It does not mention what the compilation produces (e.g., a PDF), whether any files are modified, or how to use the result. For a simple tool with two params, the description is too thin to fully guide an agent, especially given its lack of relationship to sibling tools.

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 either parameter (tex_filename, application_id) or how they relate to the compilation. The parameter names are somewhat self-explanatory, but the description adds no meaning beyond the schema, failing to compensate for the lack of schema 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 action ('Compile') and the specific resource ('generated local .tex artifact') using Tectonic. This distinguishes it from siblings like render_application_drafts, which likely generates the .tex file, making the purpose 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?

The phrase 'generated local .tex artifact' implies this tool operates on output from a prior step (e.g., render_application_drafts), giving some usage context. However, it doesn't explicitly state when to use this versus alternatives or mention any exclusions, leaving the guidance mostly implied.

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?

Without annotations, the description carries the full burden. It adds context about privacy ('private') and storage location ('locally') but doesn't disclose permissions, reversibility, or return behavior. This is a moderate level of transparency.

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 redundancy. Every phrase adds value, making it highly concise.

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 7 parameters, no annotations, and no output schema, the one-sentence description is insufficient. It omits usage context, parameter semantics, and behavioral details, leaving significant gaps for an agent.

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. It only alludes to 'job_description' but fails to explain other parameters like tags, location, work_mode, source_url, or their relationships. This provides minimal assistance.

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: 'Create a private application record and save its job description locally.' It uses a specific verb and resource, and distinguishes it from siblings like list_applications and update_application_status.

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 when creating a new application record, but does not explicitly mention when not to use it or name alternatives. It provides clear context for the primary use case, earning a 4.

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 burden. It reveals the tool creates a 'private' scaffold, implying access control, and that it depends on factual highlights. However, it does not disclose side effects, permissions, or what 'scaffold' entails in terms of behavior or output.

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, concise sentence that front-loads the primary action and purpose. No wasted words, and the structure is straightforward.

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 no output schema and no annotations, the description needs to explain what the scaffold looks like, how application_id is used, or what the return value is. It only states the input and action, leaving significant gaps for a creation 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. It directly mentions 'factual highlights', which helps clarify that parameter, but 'application_id' is never addressed. The description only partially maps to the parameters, leaving the second parameter under-defined.

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 ('Create') and resource ('interview-preparation scaffold'), and the input source ('factual highlights') adds clarity. This clearly distinguishes it from sibling tools like create_application or analyse_application_fit.

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 'from factual highlights' gives clear context for when this tool is appropriate: when you have factual highlights and need interview prep. It does not explicitly mention alternatives or exclusions, but the purpose is specific 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?

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses what the tool does NOT do (no login, no bypass, no scraping, no auto-apply), which is useful. However, it does not explicitly state whether the tool is read-only, whether it makes external network calls, or any potential side effects/rate limits. The exclusions give some transparency but leave 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 extremely concise: two sentences. The first sentence states the purpose and scope, the second provides important exclusions. Every word earns its place, and the structure is front-loaded with the essential 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?

Given the tool has 4 parameters, an output schema, and no annotations, the description provides adequate but incomplete context. It explains the overall function and explicitly notes what it does not do, which helps. However, it lacks guidance on how the parameters interconnect (e.g., what a 'board' looks like, how 'limit' behaves) and what the return structure implies. The existence of an output schema reduces the need to describe return values, but gaps remain.

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 0% description coverage, so the description must compensate. It does add meaning by listing the accepted providers ('Greenhouse, Lever, or Ashby'), which goes beyond the schema's generic 'Provider' string. However, it does not explain 'board', 'limit', or 'location_contains', although their names are somewhat self-explanatory. The coverage gap is only partially filled.

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 'Discover' and names the specific resource: 'listed jobs from a public Greenhouse, Lever, or Ashby API board.' It clearly distinguishes itself from sibling tools that focus on applications (e.g., create_application, update_application_status) by focusing on job discovery. The scope is precise, including the public API nature and the supported platforms.

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 clear context: it discovers jobs from public API boards. It also gives explicit exclusions ('This does not log in, bypass restrictions, scrape LinkedIn, or auto-apply'), which helps set when-not-to-use boundaries. However, it does not name alternative tools or explicitly state 'use this when...' but the context is strong enough to infer its intended use relative to 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It says 'private' which hints at access control, but it does not mention permissions, pagination, sorting, or any side effects. It reads as a simple read operation but omits context that an agent would need, such as whether it returns only the current user's records or all accessible private records.

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 primary action and resource, then adds the filtering option without any redundant words or filler. It is highly 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?

For a simple list tool with one optional parameter and an output schema present, the description is largely sufficient. It states what is listed and the filtering capability, and the output schema covers return values. Some missing nuance like auth scoping exists, but it is not critical for a basic list 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?

The schema's status parameter has no description, so the tool description's mention of 'optionally filtered by their status' adds meaning by explaining the purpose of the parameter. However, it does not enumerate allowed status values or provide examples, so it only partially compensates for the 0% schema description coverage.

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 the specific verb 'List' with a clear resource 'private application records', and adds a key optional filter by status. This clearly distinguishes it from sibling tools like create_application, update_application_status, and especially discover_public_jobs, which is about public jobs rather than private applications.

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 'optionally filtered by their status' implies the tool is for viewing applications and supports a filtering use case, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. There is no direct comparison to siblings, so the guidance is only implied.

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 responsibility for behavioral disclosure. It states the tool 'writes' and does so 'locally,' which implies a file-writing side effect. However, it does not mention whether files are overwritten, what permissions are needed, or any other consequences of the write operation. This is minimal disclosure.

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 without redundant words. However, it is under-specified for the complexity of the tool, so the conciseness is achieved at the expense of necessary 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?

Given the tool has 3 required parameters, no output schema, and no annotations, the description is incomplete. It explains the general output type but does not clarify how the parameters influence the output, what the tailoring brief should contain, or what 'locally' means in terms of file paths or return values.

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 explanation of the three parameters (application_id, profile_json_path, tailoring_brief). The phrase 'tailoring brief' appears but is not tied to the parameter. 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 states a specific action ('Write') and specific outputs ('editable LaTeX CV/cover-letter starters and a factual tailoring brief') with a location scope ('locally'). This distinguishes it from siblings like compile_application_tex, which focuses on compilation rather than drafting.

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. It does not mention prerequisites, exclusions, or contrast with related tools like analyse_application_fit or compile_application_tex. The usage context is only implied by the description's verb and output.

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 adds minimal context: 'one application' implies a single record, and 'private notes' suggests privacy. However, it does not disclose mutation effects, error handling, permissions, idempotency, or whether statuses are validated. This lack of behavioral detail for a write operation is a significant gap.

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 that is concise and front-loaded with the core action. It avoids fluff and uses precise qualifiers ('one', 'optional', 'private'). However, it is slightly under-specified, which limits the value of its brevity.

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 simplicity (3 parameters, no annotations, no output schema), the description is incomplete. It does not explain how to identify the application, what statuses are valid, the return value, or side effects. This is inadequate for safe usage, especially without annotation support.

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 mentions 'status' and 'notes' but does not explain their semantics beyond the schema. It omits application_id entirely. With schema description coverage at 0%, the description should compensate by explaining allowed status values, notes formatting, or parameter relationships, but it does not. The only added meaning is that notes are 'private' and that the operation targets 'one application.'

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 a specific action: 'Update one application status and optional private notes.' It identifies the resource (application) and the operation (update), which distinguishes it from sibling tools like create_application, list_applications, and analyse_application_fit. However, it does not explicitly mention how to differentiate it from alternatives, so it falls 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?

There is no guidance on when to use this tool versus alternatives. The description does not provide context such as 'use when you need to change a status' or mention any prerequisites or exclusions. It simply defines the action without situating it among the sibling tools.

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