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

The description includes '[risk: read-only]' and 'No network calls to LinkedIn', clearly indicating a safe, non-destructive operation. Since no annotations are present, the description fully carries the burden and does so effectively.

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 (two sentences) and front-loaded with a risk annotation. However, it could include the parameter and output expectations without added length, so it loses a point for missing relevant 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?

The description covers the tool's purpose and behavior well, but lacks the optional parameter targetRole and does not detail the output format (e.g., score ranges). Given no output schema, this additional context would enhance completeness.

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 optional enum parameter (targetRole) with 0% description coverage, but the description does not mention it at all. For a tool with a single parameter, this omission is a significant gap in usability.

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 and analyzes locally stored profile data and scores it for multiple dimensions. It distinguishes from sibling tools like get_profile_snapshot (retrieve) and export_profile_patch (export) by focusing on analysis and scoring.

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 after obtaining a profile snapshot, noted by 'Score the saved profile snapshot'. It explicitly states no network calls, but it does not provide explicit when-not-to-use or alternatives among 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 provided, so the description fully carries the burden. It explicitly lists risks (publishes-content, confirmation required), required OAuth scopes, the need for human approval, and the confirm flag with approvalToken. No contradictions.

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 verbose and repetitive, restating the publishing requirements. It could be condensed into a more structured format, e.g., bullet points.

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 no output schema, the description covers the core workflow adequately. However, it does not specify what the tool returns (e.g., post ID or URL), leaving a gap for agents needing 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 50%, and the description adds context for confirm and approvalToken in the workflow. However, it does not elaborate on the other parameters (text, visibility) beyond the schema, so baseline score is 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 title and description clearly state the tool creates LinkedIn posts with a draft-first workflow. It distinguishes itself from siblings by being the only post-creation tool in the list.

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 explains the required configuration (enableOfficialPosting, OAuth) and the two-step process (preview then confirm). It does not explicitly exclude use cases, but as the sole posting tool, differentiation is not necessary.

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 discloses critical behavior: [risk: local-write], nothing sent to LinkedIn, never pushes. This is transparent about safety and scope, though it could mention file overwrite behavior.

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—three short sentences. It front-loads the risk warning and gets to the point without extraneous words.

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 tool with one parameter and no output schema, the description covers purpose, behavior, and constraints. It may be missing context about dependency on generate_update_plan, but the sibling list provides that implicitly.

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 0% description coverage. The description does not explain what the parameter controls (e.g., file name, path), leaving the agent to infer from the default value 'profile-patch'.

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 writes files to the local data directory, saving an update plan as Markdown+JSON. It distinguishes from siblings like generate_update_plan by emphasizing local export and no external push.

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 says to save the most recent update plan locally and never push anywhere, implying local-only usage. However, it does not explicitly state when to use this versus generate_update_plan or other 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?

Despite no annotations, the description discloses key behavioral traits: it is draft-only and nothing is sent to LinkedIn. This clarifies non-destructive behavior, though auth or rate limits are not 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 two sentences, front-loading the risk and purpose. Every sentence adds value with 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?

The description omits the output format (e.g., list of strings) and does not mention the count parameter. Given no output schema, this gap reduces completeness 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 coverage is 0%. The description does not explain the 'count' or 'targetRole' parameters, despite the schema providing defaults, enums, and constraints. The agent lacks guidance on parameter usage.

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 it generates LinkedIn headline options with a character limit for a target role. This distinguishes it from sibling tools like rewrite_about_section or keyword_gap_analysis.

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 notes it is draft-only and local, indicating safe use for drafting. However, it does not specify when not to use it or mention 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?

The description discloses the tool is local and draft-only, indicating no data is sent and no changes are applied. This provides good transparency for a non-destructive tool, though it does not elaborate on rate limits or auth needs.

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 with two sentences that front-load the risk and local nature. Every word adds value.

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, the description explains the plan format (field, edit URL, old text, new text, rationale). It covers the main input parameter and output behavior, though it could briefly mention the return format explicitly.

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 one parameter 'changes' with a description for the 'field' property. The description adds context about the output plan containing 'edit URL' and 'old text', but does not significantly enhance understanding of the input structure beyond what the schema provides.

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 generates a manual editing plan locally without sending data to LinkedIn. It distinguishes from siblings like rewrite_* or create_linkedin_post by emphasizing the manual, draft-only nature.

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 tool is for drafting manual plans, with phrases like 'You apply changes by hand' and 'Nothing is sent to LinkedIn.' However, it does not explicitly state when to use this tool versus automated 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?

No annotations are provided, so the description carries full burden. It discloses that files are written locally and nothing is sent to LinkedIn (risk: local-write). However, it lacks details on what exactly is written (e.g., file format, location, overwrite behavior) and whether the tool returns a status or path. This is adequate but not thorough.

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 paragraph, front-loaded with risk and purpose. It efficiently conveys essential information without extraneous text. Every sentence contributes to understanding.

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 complexity (3 parameters, nested JSON, no output schema), the description is incomplete. It does not explain what the tool returns after processing (e.g., a confirmation, file path, or snapshot ID). For a file-writing tool, this is a notable gap. The behavior for different sources is described, but the output is missing.

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%, providing a baseline of 3. The description adds value beyond the schema by explaining each source enum value (e.g., 'raw copy/paste from your profile page' for pasted_text) and clarifying that the json parameter expects a 'Structured profile' and text parameter is for pasted/PDF text. This enhances 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 clearly states the tool writes files locally to ingest LinkedIn profile data from various sources (pasted text, PDF text, structured JSON, or load saved). It distinguishes from siblings like audit_profile or rewrite_experience, which modify or analyze data, 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 description lists four source types and explicitly says 'No scraping; you provide the data,' implying it should be used when a user has profile data to import. Although it doesn't directly contrast with siblings, the context suggests using this before other profile-related tools. No explicit 'when not to use,' but still clear.

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 includes '[risk: read-only]' and explicitly states 'No network calls to LinkedIn,' which clearly indicates the tool is safe and has no side effects. Since no annotations are provided, these statements effectively compensate. However, it does not mention any potential constraints like data volume limits or prerequisites.

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 very concise: two sentences plus a bracketed risk tag. Every sentence adds value, and the risk indicator is front-loaded. No unnecessary words or 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 the lack of output schema, the description adequately outlines what the tool does and roughly what it returns. It covers the core functionality and safety. However, it does not specify the format or structure of the recommendations (e.g., list of keywords with scores), which would be helpful for full completeness.

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 adds significant meaning beyond the schema by linking the two parameters: it explains that jobDescriptions can be used directly, or targetRole serves as a keyword bank. It also hints at the output (missing keywords + natural placement). With 0% schema description coverage, this is essential context. However, it could elaborate on default behavior when jobDescriptions is empty.

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 it reads/analyzes locally stored profile data and compares against job descriptions to recommend missing keywords. The verb 'compare' and 'recommend' specify the action, and it distinguishes from siblings like audit_profile or rewrite_about_section by focusing on keyword gaps. However, the purpose could be more explicit about the output being a list of keywords with placement suggestions.

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 a user wants to identify missing keywords for a target role. However, it does not explicitly state when not to use it, nor does it mention alternatives among siblings (e.g., audit_profile for a different type of analysis). Guidance is implicit but not comprehensive.

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 clearly discloses that the tool opens a browser, requires confirmation, and does not auto-save. This provides important behavioral context beyond what structure provides, especially 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?

The description is somewhat repetitive, stating the same opening action twice. It could be more concise, though the risk and confirmation notes are helpful.

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 covers purpose and key behavioral traits but lacks parameter details, usage guidelines, and return information. Given no output schema and no annotations, it is adequate but not thorough.

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 33% coverage (only section described), and the description adds no additional meaning to parameters. The 'two-step confirmation' hint relates to confirm but is not explicit. Parameters like approvalToken remain unexplained.

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 opens a LinkedIn edit page for manual editing, specifying the action and resource. This distinguishes it from sibling tools like rewrite_about_section or create_linkedin_post, which have different purposes.

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 tool is for manual editing by stating 'no automation, no auto-save,' but does not explicitly state when to use it over alternatives or provide exclusions. No sibling tools are mentioned for comparison.

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 burden. It discloses that the tool generates drafts locally without sending data to LinkedIn, which is critical safety information. It does not mention authentication or rate limits, but the local-only guarantee suffices.

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, both front-loaded with essential info: risk/draft/local first, then purpose and styles. No fluff; every word adds value.

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 2 parameters, no output schema, and no annotations, the description covers the main purpose and styles. It lacks explanation of 'extraContext' and return values, but the safety info and variant list make it fairly complete.

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 compensate. It lists the enum values for 'styles' (e.g., 'concise', 'technical'), adding meaning beyond the raw schema. However, the 'extraContext' parameter is not described, leaving a gap.

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 verb 'Generates' with the resource 'draft text' for the About section, clearly specifying the output. It lists five distinct styles, making the tool's purpose unambiguous. This differentiates it from sibling tools like 'rewrite_experience' and 'generate_headline_variants'.

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 states '[risk: draft-only]' and 'Nothing is sent to LinkedIn,' implying safe experimentation. This guides when to use: for local drafts without risk. However, it does not mention when not to use or compare to alternatives like 'rewrite_experience'.

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 full behavioral disclosure. It clearly states the tool is 'draft-only', generates text locally, and does not send data to LinkedIn. It also warns against inventing metrics, which is a critical behavioral constraint.

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 with no wasted words. It front-loads the risk warning and then efficiently states purpose, behavior, and constraints. Every sentence provides essential 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 parameters, one required nested object, and no output schema, the description adequately covers purpose, risk, parameter usage constraints, and behavioral traits. It could be more explicit about output characteristics, but the local draft nature is clear.

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%, but the description adds value with warnings and clarifications, such as 'Real metrics you remember... NEVER invent metrics' for knownMetrics, and 'The role to rewrite' for the experience object. This enhances meaning beyond 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 tool rewrites job experience bullets with specific improvements (strong verbs, technical keywords, measurable impact), and the name and title reinforce this. It distinguishes itself from sibling tools like 'rewrite_about_section' by targeting experience bullets.

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 explicit when-to-use guidance: 'Rewrite job experience bullets' and includes important constraints like 'Never invents metrics — supply knownMetrics' and 'Generates draft text locally. Nothing is sent to LinkedIn.' While it doesn't explicitly list alternatives, the sibling tools list provides context.

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