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

Annotations already declare destructiveHint=true, and the description adds 'clean up resources' which is consistent but generic. It does not detail what resources are cleaned or the irreversible nature beyond the annotation, but it does not contradict 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?

Single sentence, front-loaded with the primary action, no wasted words. Perfectly concise for the tool's simplicity.

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 no parameters and a simple destructive action, the description is complete. An output schema exists (as per context signals), so return information is not required here. The description fully covers the tool's function.

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?

With zero parameters, the schema covers everything vacuously. The description adds no parameter-level detail because none exist. Baseline 4 is appropriate for a parameterless 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 states the verb 'close' and the resource 'browser session', with a specific cleanup action. It is distinct from all sibling tools, which are getters/search tools or actions like connect/send.

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 you need to end the session) but provides no explicit when-to-use or when-not-to-use guidance, nor mentions alternatives. As the only session-ending tool among siblings, context is assumed but not stated.

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?

Annotations already declare destructiveHint, and the description adds that 'MCP clients will prompt for user confirmation before execution,' which provides some behavioral context. However, it does not explain side effects beyond confirmation, such as potential duplicate requests or permission requirements, leaving room for more 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 two sentences with no fluff. It leads with the primary purpose and then notes the annotation implication. Every word earns its place, making it appropriately concise and front-loaded.

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 a clear action (connection request/accept), full schema coverage, and annotations covering safety, the description is sufficiently complete. It doesn't need to elaborate on return values since an output schema exists, and the action is straightforward. Minor gaps like error handling or idempotency could be added, but they aren't essential.

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 provides full descriptions for both parameters (linkedin_username and note), so schema description coverage is 100%. The description itself adds no extra parameter meaning beyond what is already in the schema, matching the baseline of 3.

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: 'Send a LinkedIn connection request or accept an incoming one.' This specifies the verb (send/accept) and resource (connection request), and distinguishes it from siblings like send_message and get_inbox, making its 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?

The description implies when to use the tool by stating its purpose, but it does not explicitly provide context or alternatives. There is no mention of when not to use it or comparisons to similar tools, so the guidance is only implicit.

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?

Annotations already declare readOnlyHint and openWorldHint, but the description adds behavioral context: it derives data from a specific LinkedIn page, exposes unique demographics, and warns about fewer result pages compared to search_people. It also clarifies the slug requirement.

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 multi-paragraph and detailed, but every sentence adds value—use cases, alternatives, parameter constraints, and an example. While slightly longer than strictly necessary, it's efficiently structured around purpose, usage, and uniqueness.

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 annotations (readOnlyHint, openWorldHint), the description covers all necessary behavioral context: output includes aggregates, page limits relative to search_people, and the surprising slug mismatch. With an output schema and both params documented, no critical 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?

Schema describes both parameters with examplesags: company_name is a slug, keywords is optional filter. The description elaborates on the slug format and gives an example, but doesn't fully detail keyword matching semantics beyond 'name, title, or skill.' Schema coverage is 100% and description reinforces it, so a high score is warranted.

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:

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly directs users to search_people for filtered searches by degree/location and notes the /people/ tab limitation, providing clear exclusions.

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?

Annotations already declare readOnlyHint and openWorldHint. The description adds no extra context about authentication, rate limits, or side effects. It does not contradict the annotations, but it also does not provide additional behavioral details beyond what the annotations already imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no unnecessary words or repetition. It is well-structured and directly states the tool's function.

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 and the description sufficiently covers its purpose. Since an output schema exists (per context signals), the description does not need to explain return values, and no additional context is required for this straightforward 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 provides a description for the only parameter (company_name) with examples. The tool description does not add further semantic meaning beyond the schema, and since the schema coverage is high, the baseline of 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?

The description clearly states the action ('get') and the resource ('recent posts from a company's LinkedIn feed'). It effectively differentiates from sibling tools like 'get_company_profile' or 'get_company_employees' by specifying the data type (posts).

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 explicitly state when to use this tool versus alternatives, nor does it provide conditions or exclusions. However, the purpose is so straightforward that the usage context is implicitly clear for someone familiar with LinkedIn 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?

The annotations (readOnlyHint=true, openWorldHint=true) already indicate a read-only, side-effect-free operation. The description does not contradict these hints and adds no additional behavioral detail such as rate limits or authentication requirements, which would have improved 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, concise sentence that immediately conveys the tool's purpose. It is front-loaded and free of unnecessary wording, making it efficiently scannable.

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 simplicity of the tool, the description is adequate. It conveys the core function, and the schema covers parameter details. However, it might slightly benefit from mentioning that it scrapes the profile (as implied in the schema), but this is not essential for basic usage.

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 provides high coverage (100%) with detailed descriptions for both parameters, including examples and defaults. The description itself adds no extra meaning beyond the schema, so it does not enhance 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 clearly states the tool's function: 'Get a specific company's LinkedIn profile.' It uses a specific verb ('Get') and resource ('company's LinkedIn profile'), which distinguishes it from sibling tools like get_company_posts and get_company_employees.

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 no guidance on when to use this tool versus the sibling tools. It does not mention any conditions or alternatives, leaving the user to infer usage from the name alone.

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 that visiting UI rows 'may also mark them as read' (unusual if no read hint provided). It also explains how the UI's restrictions make enumeration necessary, and the side effect makes the agent more informed.

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?

Dense, layered description that explains LinkedIn UI limitations and the match between the index and thread IDs. Each sentence adds information, but it's somewhat lengthy as it packs in all behavior.

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?

Input schema is complete, output schema, openWorldHint, descriptions of parameter semantics, but no mention of errors, permissions, or result shape (output schema fills that). Adequate for given complexity.

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 documentation is 100% covered and describes 'index' behavior with 0-based selection and its precedence relationship to thread_id; the description of the lookup parameters adds contextual nuance beyond schema.

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 clear action ('read a specific conversation') and distinguishes it as one conversation by username or ID. Sibling tools like get_inbox list all messages, so the 'specific' scope is evident. It lacks explicit sibling differentiation, but the verb+object is 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?

Explains the linkedin_username lookup path, what it does (enumerating rows), and when to pass thread_id directly 'to skip this enumeration'. It says it's 'the only available path' to justify behavior. No explicit alternatives list, but usage implication is strong.

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 readOnlyHint and openWorldHint annotations indicate a safe, read-only operation, but the description does not disclose how pagination/loading batching affects returned counts, and does not mention the tool's behavior beyond a simple feed retrieval.

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 concise sentence and the schema is self-contained; no redundant 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?

There is an output schema that likely defines post objects, but the description does not clarify the shape or sort order of returned data; instructions for scenarios like over-fetching or pagination are not included in the description.

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 while having 100% description coverage adds important context about batching behavior. The default value, range, and explanation of the number field's influence are described clearly.

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 retrieves posts from the authenticated user's LinkedIn feed, but does not differentiate it from sibling tools like search_posts or get_company_posts.

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 such as search_posts or get_inbox; no exclusions or prerequisites are mentioned.

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 annotations already declare readOnlyHint=true and openWorldHint=true, covering the tool's safety profile. The description adds minimal behavioral context (e.g., 'recent' as a filter, but no details on sorting, pagination, or side effects). It does not contradict annotations and provides some context beyond them, so a 3 is appropriate.

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 essential action and scope. It has no redundancy or filler, maximizing clarity in minimum 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?

The tool is simple with one optional parameter, an output schema is present, and annotations cover safety. The description adequately defines its function for the agent to select and invoke correctly. Minor omissions like pagination behavior or recentness definition could slightly enhance completeness, but given the simplicity and schema coverage, a 4 is reasonable.

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 100% description coverage for the single parameter 'limit' with clear constraints (1-50, default 20). The description does not add further parameter-specific detail, but given full schema coverage, the baseline 3 is correct.

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 verb ('List') and a resource ('recent conversations from the LinkedIn messaging inbox'). It is distinguishable from sibling tools like get_conversation (fetches a single conversation) and search_conversations (searches/filters), so it fully specifies 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 implies usage by stating it lists inbox conversations, but it does not explicitly differentiate when to use this tool versus alternatives (e.g., get_conversation for a specific conversation or search_conversations for filtering). While the context is evident from the name and description, no explicit 'when not to use' is provided, so it earns a 3.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to repeat safety. It adds no extra behavioral context (e.g., rate limits, auth requirements, or what 'details' includes). The description is consistent with annotations, so no contradiction, but it adds little beyond the structured data.

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, concise sentence that is front-loaded with the action and resource. It is appropriately sized for a simple tool with one parameter, though it could add a bit more context without becoming verbose.

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 (one parameter, output schema present, annotations provided), the description is adequate but minimal. It doesn't explain what 'job details' includes or any edge cases, but the output schema likely covers return values. It is complete enough for a straightforward retrieval 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 100% for the single parameter job_id, which includes an example. The description adds no additional meaning beyond the schema, so the baseline of 3 is appropriate. No extra context about the parameter's format or constraints is provided.

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 retrieves job details for a specific LinkedIn job posting, using a specific verb ('get') and resource ('job details'). It distinguishes from siblings like search_jobs and get_saved_jobs by focusing on a single job ID, though it doesn't explicitly name alternatives.

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 specific job ID is known, but it does not explicitly state when to use this tool versus alternatives like search_jobs or get_saved_jobs. No exclusions or alternative tool names are provided, so guidance is minimal but not misleading.

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?

Annotations already declare readOnlyHint and openWorldHint. The description adds valuable behavioral context by explaining the navigation to /in/me/ and the redirect resolution that affects the returned url field. It also implies authentication requirements without contradicting 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 concise and front-loaded: one clear purpose sentence followed by a short, valuable explanation of the redirect behavior. Every sentence earns its place without 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 tool has strong annotations, full schema coverage, and an output schema. The description adds the key distinguishing behavior (URL resolution) and implies auth requirements. It lacks explicit mention of error cases or session prerequisites, but given the available structured data, it is sufficiently 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?

The input schema has 100% coverage with detailed descriptions for both parameters (sections and max_scrolls). The tool description itself adds no parameter-specific meaning beyond what the schema already provides, so the baseline of 3 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 description states 'Get the authenticated user's own LinkedIn profile' with a specific verb and resource. The word 'own' clearly distinguishes it from the sibling tool get_person_profile, 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?

The description clearly implies this tool is for the authenticated user's own profile, contrasting with get_person_profile for others. However, it doesn't explicitly name alternative tools or state when not to use it, so it stops short of full usage 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?

Annotations declare readOnlyHint=true and openWorldHint=true, so the safety profile is clear. The description adds context about optional sections and pagination behavior (max_scrolls) which helps set expectations. It doesn't repeat annotation info, adding value on how the tool scrapes sections, though it could be more explicit about potential side effects (none) or rate limiting. Given annotations cover read-only nature, a 4 is appropriate.

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 clear sentence, front-loaded with the action. It's concise, but it lacks detail on options that the schema covers, making it slightly under-specified as a standalone description. However, given the schema's richness, it's appropriately brief. It earns a 4 for efficiency.

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 a rich schema (100% param coverage) and an output schema present, the description doesn't need to explain return values. The description covers the primary purpose and the schema handles details. It is complete enough for a straightforward read operation, though it doesn't mention error scenarios. Given the annotations, a 4 is fair.

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 already provides 100% coverage of parameters with detailed descriptions (e.g., sections format, max_scrolls behavior). The description doesn't add additional parameter meaning beyond what's in the schema, so baseline 3 is justified. It does mention the main parameter implicitly in 'specific person', but that's minimal.

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 retrieves a specific person's LinkedIn profile using a username, which distinguishes it from siblings like get_my_profile and get_company_profile. It is specific verb+resource with the required parameter noted.

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 for retrieving a profile by username, and the schema adds context on optional sections. However, it doesn't explicitly contrast with sibling tools like search_people or get_sidebar_profiles, but the purpose is clear enough for an agent to select it when a known username is provided.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description need not repeat safety. It adds a useful detail that the tool returns job_ids for further lookup, but it does not disclose pagination specifics, rate limits, or empty-result behavior. This is adequate but not rich, matching the baseline for tools with these 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 extremely concise: two sentences, no fluff, with the primary purpose front-loaded and a clear follow-up usage note. 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?

For a simple tool with one optional parameter, a read-only annotation, and an output schema present, the description is complete. It states what it does, what it returns, and how to use that return value, covering all essential use-case context.

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 only parameter, max_pages, is fully described in the schema with its range and default. The description adds no additional semantic meaning, so the baseline of 3 applies per the rubric when schema coverage is high (100%).

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 ('List') and clearly identifies the resource ('job postings saved by the authenticated LinkedIn user'). It distinguishes itself from sibling tools like search_jobs (searches all jobs) and get_job_details (details for a specific job) by focusing on saved posts, and it even hints at a downstream workflow with get_job_details.

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 clearly states what it does and mentions that returned job_ids can be passed to get_job_details, implying a workflow. However, it does not explicitly discuss when not to use this tool or directly contrast it with alternatives like search_jobs, though the context of 'saved' makes the use case 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 readOnlyHint annotation is respected—the description only retrieves data and does not imply any modification. It clearly states the actions (follows links, skips premium sections) and avoids contradicting the annotation. Since annotations already indicate read-only, the description adds value by detailing the exact procedural 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 concise, using two sentences to convey the core function and key details. It avoids redundancy, though the first sentence is somewhat generic and could be merged with the specifics, but overall it is well-structured and to the point.

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 one input, and the description adequately explains the output (profile links) and key behaviors (following 'Show all', skipping premium). It lacks explicit error handling or edge-case mentions, but given the simplicity and absence of an output schema, it is sufficiently complete for an agent to use correctly.

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 fully describes the single parameter (linkedin_username) with a clear example. The description adds no additional semantic nuance beyond what is already in the schema, so the baseline of 3 applies given 100% schema 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 clearly states the tool extracts profile links from specific sidebar sections, using precise section names. It distinguishes itself from sibling tools like get_person_profile or search_people by focusing on sidebar recommendations, 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 implies usage for obtaining profile recommendations from a page's sidebar, but does not explicitly contrast with alternatives like get_person_profile or search_people. However, the detailed behavior (following 'Show all', skipping premium) provides implicit context for when this tool is appropriate.

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 annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds no additional behavioral context—it does not mention what the search returns (e.g., a list of matches, basic company info), pagination, rate limits, or how results relate to other tools. With annotations covering the safety and scope, the description contributes nothing beyond them.

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 with no redundancy or filler, making it maximally concise. Every word contributes to the core purpose, and it is appropriately sized for a simple search tool with one parameter.

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 (one parameter), the presence of an output schema (so return format is covered), and annotations for read-only/open-world, the description is minimally adequate. However, it lacks any indication of what types of results to expect or how they relate to other endpoints, which could leave the agent without enough context to decide if this is the right search 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 100% because the single parameter 'keywords' has an adequate description with examples. The tool description does not add any extra meaning about the parameter beyond what the schema already provides, aligning with the baseline of 3 for high 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 'Search for companies on LinkedIn' clearly identifies the action (search) and resource (companies) within a specific platform, distinguishing it from sibling search tools like search_people or search_jobs. However, it does not explicitly mention any filtering or scope beyond the resource type, so it stops 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, such as get_company_profile for detailed company information or get_company_employees for employee lists. The description provides no context about use cases, prerequisites, or typical scenarios, leaving the agent to infer when this search is appropriate.

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?

Annotations are minimal (only openWorldHint), so the limit parameter's note adds important context: each enumerated result selects a row in LinkedIn's UI and may mark it as read. This is a valuable behavioral disclosure beyond annotations. No contradiction exists.

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. It is appropriately concise for a simple search tool and avoids redundancy with the schema.

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 low-complexity tool with full schema coverage and an output schema, the combination of the terse description and the limit-parameter side-effect warning is sufficiently complete. It would benefit from explicit scoping (e.g., searches only the user's conversations) and sibling differentiation.

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 baseline applies. The tool description adds little beyond the schema: 'keywords' is self-explanatory, and the detailed limit behavior is already part of the input schema.

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 ('Search') and resource ('messages'), and the tool name clarifies the target is conversations. It is distinguishable from sibling tools like search_people and search_posts by resource, but it doesn't explicitly mention that results are conversation references.

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?

Usage is implied by 'Search messages by keyword'—use when you need to find conversations by keyword rather than listing all via get_inbox. However, no explicit when-to-use or alternative guidance is provided.

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?

Annotations include readOnlyHint: true and openWorldHint: true, indicating this is a read-only operation. The description adds minimal extra context about the returned job_ids being used for get_job_details, which is helpful. It doesn't contradict 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 brief, two sentences, and immediately states the core function. The second sentence provides a valuable integration note about get_job_details. No wasted 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?

Given the output schema exists and annotations are present, the description is adequately complete for a search operation. The integration note about job_ids adds important context. Minor gap: could mention if results are paginated or any default sorting, but not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all parameters. The description adds a helpful note about job_ids for get_job_details. The description mentions 'job_ids' but doesn't detail all parameters, which is acceptable since the schema covers everything else.

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 starts with 'Search for jobs on LinkedIn' which is a clear verb+resource. It distinguishes this tool from siblings by describing it simply. However, it could do more to differentiate from other search tools like search_people or search_posts, though the context of 'jobs' helps.

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 doesn't explicitly state when to use this over alternatives, but the context of searching LinkedIn jobs is clear. It doesn't give exclusions or alternatives, but the sibling list shows search tools for other entities, making the usage intent somewhat implicit.

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?

Annotations already declare readOnlyHint and openWorldHint, so the description need not repeat those. The current_company parameter description adds significant behavioral transparency by disclosing that plain company names are ignored by LinkedIn and only numeric URNs work, which is valuable real-world behavior beyond 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 main description is a single, direct sentence with no filler. The parameter descriptions are detailed but clearly structured, front-loading the required keyword parameter first. Every element 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?

The tool has an output schema and annotations that cover the safety profile. The description is minimal but sufficient when combined with schema descriptions, which explain key filtering behaviors. Some overview of result characteristics is missing, but the output schema likely covers that.

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 parameters already have detailed descriptions. The main description adds no parameter semantics. The schema descriptions thoroughly explain network codes and the current_company URN requirement, meeting the baseline but not exceeding it.

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 'Search for people on LinkedIn' uses a specific verb and resource, clearly distinguishing it from sibling tools like search_companies and search_jobs. The scope is explicit, making the tool's 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 main description lacks explicit when-to-use guidance, but the current_company parameter description provides a concrete alternative: use get_company_employees for company-wide demographics and get_company_profile for URN lookup. This gives situational context, though overall usage guidance is limited to edge cases.

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 goes beyond the readOnlyHint and openWorldHint annotations by explaining that content search is an infinite scroll and that max_pages caps the scroll depth rather than fetching discrete pages. This is critical operational behavior that the annotations alone would not convey.

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 and front-loaded with the core purpose in the first line, then expands with usage context and differentiations. Every sentence adds value—the hiring-use case example, the global vs. feed distinction, and the infinite-scroll caveat all earn their 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?

With an output schema, the description need not explain return values. The combination of description, annotations (read-only, open-world), and thorough schema (all parameters documented with defaults and constraints) covers everything an agent needs to decide when and how to use this tool correctly. Actual use-case guidance and behavioral details complete the 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?

The schema description coverage is 100%, so the baseline is 3. The description adds value for keywords by providing example patterns ('Buscamos Unity', 'AI automation hiring') and clarifies the infinite-scroll semantics of max_pages. The date_posted parameter is fully documented in the schema with accepted spellings.

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 searches LinkedIn posts/content globally by keyword, specifically the 'Posts' tab. It distinctly differentiates from siblings like get_feed (own home feed) and get_company_posts (one company's page), making it unambiguous what this tool does.

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 explains when to use this tool: to catch informal hiring posts that often precede formal job listings. It also provides clear exclusions by naming alternative tools (get_feed and get_company_posts) for different use cases, giving agents direct decision criteria.

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?

Beyond the annotations (destructiveHint and openWorldHint), the description clarifies that the write happens only when confirm_send is True, which is a safeguard. It also adds the requirement for direct messageability. This extra context helps the agent understand the tool's behavior without relying solely on 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 extremely concise: two sentences that immediately state the purpose and key constraint. It front-loads the core function and avoids unnecessary elaboration, making it easy for an agent to scan.

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 write operation, the description covers the essential behavioral prerequisites (messageability, confirm_send flag) and relies on the schema for parameter details. It does not mention authentication or output, but those are supplied by annotations and the presence of an output schema. The description is adequate for the tool's complexity.

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 already provides complete descriptions for all four parameters (100% coverage), so the tool description does not need to repeat them. It does not add any additional meaning beyond what the schema gives, which is the baseline expectation.

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 (send) and target (a LinkedIn user), with an important qualifier about direct messageability from the profile page. This establishes the tool's core purpose and differentiates it from read-only LinkedIn tools by explicitly labeling it a write operation.

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 a prerequisite (the recipient must be directly messageable) and notes that the send only occurs when confirm_send is True, implicitly advising caution. However, it does not mention when to choose this tool over alternatives like connecting first or using the inbox, so guidance on context and exclusions is limited.

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