Server Quality Checklist

Tool Scores

• add_linkedin_educationC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full disclosure burden. It only says 'Add,' implying a write operation, but does not mention duplicate handling, whether existing education entries are affected, permission requirements, or success/failure behavior.

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

  Conciseness4/5

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

  The description is a single short sentence with no filler and is easy to parse. It is appropriately front-loaded, though it is too minimal to provide substantive guidance.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a 9-parameter mutation tool with no annotations and no output schema, this description is incomplete. It does not explain what the response looks like, which parameter is required, or any behavioral caveats, leaving the agent reliant entirely on the schema.

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

  Parameters3/5

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

  Schema description coverage is 100%, and every parameter already has a clear description in the schema. The tool description adds no parameter-level meaning, but that is acceptable under the baseline because the schema does the heavy lifting.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific action ('Add') and resource ('education') on a LinkedIn profile, so an agent can tell what the tool does. However, it largely restates the tool name and does not explicitly differentiate itself from sibling add_* tools beyond the resource name.

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

  Usage Guidelines2/5

  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 like add_linkedin_skill, add_linkedin_position, or add_linkedin_certification. No prerequisites, profile-state conditions, or exclusion criteria are mentioned.

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

• add_linkedin_languageC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full behavioral burden, but it only says 'Add' without disclosing side effects, overwrite behavior, idempotency, or what a successful call returns. An agent cannot anticipate whether an existing proficiency is replaced, appended, or rejected.

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

  Conciseness5/5

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

  The description is one clean, front-loaded sentence with no filler or redundant restating of the tool name. It communicates the essential purpose immediately.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Although the tool is simple and the schema is rich, the absence of annotations and the lack of behavioral or usage context leave an agent without enough information to know the consequences of the call or how to handle errors. The description is minimally viable but incomplete for robust tool selection and invocation.

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

  Parameters3/5

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

  The input schema already documents both parameters, including the proficiency enum, so the description adds no further semantic value. Since schema coverage is 100%, the baseline score of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Add') and identifies the exact resource ('a language to your LinkedIn profile'), so an agent can tell what operation is being exposed. It does not explicitly distinguish itself from sibling add_* tools, but the object differs clearly from them.

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

  Usage Guidelines2/5

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

  There is no guidance about when this tool should be chosen over alternatives, such as add_linkedin_skill or the delete_linkedin_language sibling. The intended context must be inferred entirely from the tool name and description.

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

• add_linkedin_publicationC
  2.9/5.0
  Behavior2/5

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

  Annotations are not provided, so the description carries the full burden of behavioral disclosure. It only restates the action without revealing side effects, authentication needs, duplicate handling, or the nature of the response, offering minimal transparency for a mutating operation.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with no filler or redundant content. Every word contributes to stating the core purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no annotations, no output schema, and seven parameters, the one-sentence description is too sparse to be contextually complete. It omits return value expectations, failure behavior, and any guidance on how the optional date or publisher fields interrelate.

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

  Parameters3/5

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

  The input schema covers 100% of the parameters, each with a description, so the schema carries the parameter-level meaning. The tool description adds no additional semantic context beyond what the schema already provides, matching the baseline for full schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('Add') and the resource ('a publication to your LinkedIn profile'), making the tool's purpose immediately obvious. It does not explicitly distinguish itself from sibling add_* tools, but the resource type is specific enough for basic differentiation.

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

  Usage Guidelines2/5

  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, nor any mention of prerequisites or context. The only implied usage is 'when you want to add a publication,' which is not sufficient guidance beyond the name itself.

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

• delete_linkedin_educationC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It only restates that the tool deletes education and does not mention whether deletion is irreversible, whether special permissions are required, or what side effects occur. For a destructive operation, this is a significant transparency gap.

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

  Conciseness5/5

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

  The description is one short, focused sentence with no filler or redundancy. It front-loads the action and target, making it easy to parse quickly.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a destructive operation with no annotations and no output schema, the description is too thin. It provides the action and target, but omits irreversibility, ownership requirements, and result behavior, leaving an agent without enough context to fully anticipate the consequences of calling the tool.

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

  Parameters3/5

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

  Schema description coverage is 100%, with educationId already clearly described as 'The ID of the education entry to delete'. The description adds no additional parameter meaning, so the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb and resource: 'Delete education from your LinkedIn profile'. It clearly identifies the operation and target, and is distinct enough from sibling deletion tools by naming the education resource. However, it does not explicitly clarify that it deletes a single education entry rather than the whole education section.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool instead of delete_linkedin_language, delete_linkedin_position, or other sibling deletion tools. The intended use is implied by the resource name, but the description offers no exclusions, prerequisites, or alternative routing.

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

• delete_linkedin_skillC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It states that the skill is deleted but does not disclose whether the deletion is permanent or irreversible, whether profile-owner authorization is required, or what happens if the skill does not exist.

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

  Conciseness4/5

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

  The description is a single, front-loaded sentence with no filler. It is concise, though it achieves conciseness by omitting contextual details.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple with one fully documented parameter, so the description covers the basic invocation. However, there is no output schema or annotation coverage, and the description omits destructive-operation caveats and any statement about return or error behavior.

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

  Parameters3/5

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

  Schema coverage is 100% and the schema already describes skillId as 'The ID of the skill to delete'. The description adds no further meaning about where to obtain the skill ID or how it must be formatted.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Delete'), resource ('skill'), and scope ('from your LinkedIn profile'), making the action unambiguous. It does not explicitly contrast with sibling deletion tools like delete_linkedin_language, but the resource name and phrasing distinguish it enough.

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

  Usage Guidelines2/5

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

  There is no guidance about when to use this tool versus alternatives such as add_linkedin_skill or delete_linkedin_language, and no prerequisites or exclusions. The intended usage is only implicit in the verb and resource.

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

• search_linkedin_peopleC
  2.9/5.0
  Behavior2/5

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

  There are no annotations, so the description carries the full burden of behavioral disclosure. It only says 'Search for people on LinkedIn' and does not mention result format, pagination behavior, authentication requirements, rate limits, or what distinguishes a search result from a profile object.

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

  Conciseness4/5

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

  The description is very short and front-loaded, with no filler. However, it is perhaps too terse to fully support tool selection and invocation, though that is more a completeness issue than a conciseness issue.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema, no annotations, and only a one-sentence description, the definition leaves significant gaps: what the search results look like, how pagination works, whether results are sorted, and how this tool relates to the other LinkedIn tools. The simple parameter list is documented, but the surrounding operational context is lacking.

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

  Parameters3/5

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

  Schema description coverage is 100%, with both 'keywords' and 'limit' documented. The description adds no parameter-level meaning beyond the schema, which is acceptable per the baseline. It does not clarify how keywords are matched or how limit interacts with default behavior beyond the schema's mention.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a clear action ('Search') and resource ('people on LinkedIn'), which is enough to identify the core function. It does not explicitly differentiate from sibling tools like get_linkedin_connections, but the verb 'search' suggests a broader discovery operation rather than retrieving an existing list.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool versus siblings such as get_linkedin_profile or get_linkedin_connections. There are no exclusions, alternative conditions, or examples that would help an agent choose between search and direct retrieval.

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

• share_linkedin_postC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description must carry the behavioral disclosure burden. It mentions the sharing action and attachment options but does not state that the post is public, that it is irreversible, whether authentication is required, or what happens on failure (e.g., invalid image URL).

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with no filler or redundancy. It efficiently captures the core action and the main optional content types in just a few words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a mutation tool with six parameters, no annotations, and no output schema, the description is thin on operational context. It omits important guidance about when to choose this tool over the sibling, what side effects to expect, and what a successful invocation returns.

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

  Parameters3/5

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

  The schema already documents all six parameters with 100% coverage, so the baseline is 3. The description adds some value by grouping the image options (URL, prompt, Nano Banana) and article link, but it does not substantially deepen understanding of the parameters beyond what the schema provides.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the action ('Share a new post on LinkedIn') and the resource, with specific attachment options. However, it does not explicitly distinguish this from the sibling 'generate_and_share_linkedin_post', so there is minor ambiguity in tool selection.

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

  Usage Guidelines2/5

  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 closely related 'generate_and_share_linkedin_post', nor does it explain exclusions, prerequisites, or which tool should be chosen for AI-generated post content. The usage context is left entirely to inference.

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

• add_linkedin_positionB
  3.2/5.0
  Behavior2/5

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

  With no annotations, the description must disclose behavioral traits, but it only states the basic add action. It does not mention side effects, whether an existing position is replaced, authorization requirements, or any constraints around the 'current' and date fields.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with no filler or redundant phrasing. Every word contributes to conveying the core action.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a mutation tool with no annotations and no output schema, the description is underspecified. It omits important context such as whether authorization is required, how the tool behaves when 'current' conflicts with end dates, and how this differs from update/delete siblings. The schema covers parameters, but the overall guidance is minimal.

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

  Parameters3/5

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

  The input schema already describes all 8 parameters with 100% coverage, so the description does not need to repeat them. The description adds no extra meaning beyond the schema, which is acceptable at baseline.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Add') and resource ('work position') with a clear target ('your LinkedIn profile'). It efficiently distinguishes this from sibling tools like add_linkedin_skill or update_linkedin_position.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool versus update_linkedin_position or delete_linkedin_position. There is no mention of prerequisites, such as needing an authenticated LinkedIn session, or when adding is preferable to updating an existing position.

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

• get_linkedin_connectionsB
  3.3/5.0
  Behavior2/5

  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 only says 'Get', implying a read operation, but does not mention authentication requirements, rate limits, pagination, or what is actually returned. This is minimal behavioral transparency for a tool with zero annotation support.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with no filler. Every word contributes to meaning, and it is appropriately sized for such a simple tool.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple and the schema covers its only parameter, so the description is minimally adequate. However, with no output schema and no annotations, the agent would benefit from knowing whether it returns a list of profiles, profile URLs, or other details, and whether any authorization scope is needed.

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

  Parameters3/5

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

  Schema description coverage is 100% for the single parameter 'limit', so the schema already documents the parameter adequately. The description adds no additional parameter semantics, so the baseline score of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Get') and a clear resource ('the user's LinkedIn connections'), making the tool's primary function obvious. It does not explicitly distinguish itself from siblings like get_linkedin_profile or search_linkedin_people, but the resource name is distinct enough to avoid major confusion.

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

  Usage Guidelines3/5

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

  The description implies usage through the verb and resource: call this to retrieve the user's LinkedIn connections. However, it gives no explicit when/when-not guidance and does not mention alternatives such as search_linkedin_people for finding non-connection people.

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

• add_linkedin_skillB
  3.4/5.0
  Behavior2/5

  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, but it only restates the action implied by the tool name. It does not mention whether the skill already exists, how duplicates are handled, whether authentication is needed, or what side effects occur beyond adding the skill.

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

  Conciseness5/5

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

  The description is a single, clear sentence with no filler or redundant phrasing. It front-loads the action and object, making it easy to scan and understand instantly.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the low complexity—one required parameter, no nested objects, and no output schema—the description plus schema is largely sufficient for an agent to invoke the tool correctly. The main gap is the lack of any behavioral context (e.g., response format, duplicate handling), but the simplicity of the operation keeps this from being a major omission.

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

  Parameters3/5

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

  The schema already documents the only parameter ('name') with full 100% coverage, so the description does not need to repeat it. The description adds no extra semantic detail about the parameter, which matches the baseline for a fully schema-covered simple parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Add') and a clear resource ('a skill to your LinkedIn profile'), making the tool's purpose immediately obvious. It also distinguishes this tool from siblings like add_linkedin_language or delete_linkedin_skill by naming the exact object being modified.

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

  Usage Guidelines2/5

  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 instead of related tools, nor does it mention any prerequisites or limitations. There is no explicit or implied comparison with alternatives like delete_linkedin_skill or add_linkedin_language.

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

• update_linkedin_positionB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It only says 'Update,' which conveys mutation, but it does not disclose whether unspecified fields are preserved or cleared, whether the change is reversible, or any permissions/authentication requirements.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with no filler. It communicates the essential operation clearly and efficiently.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no annotations and no output schema, the description is too thin for an update tool. It does not address partial-update behavior, return values, or failure conditions, all of which are relevant for an AI agent invoking this tool correctly.

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

  Parameters3/5

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

  Schema description coverage is 100%, and each parameter already has a clear description in the input schema. The tool description adds no additional meaning beyond what the schema 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.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('Update') and the resource ('an existing position on your LinkedIn profile'). It distinguishes itself from sibling tools like add_linkedin_position and delete_linkedin_position by explicitly targeting existing positions.

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

  Usage Guidelines3/5

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

  The word 'existing' implies this is for modifying an already-created position rather than adding or deleting one, but there is no explicit when-to-use guidance or mention of alternatives. The context is implied rather than stated.

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

• add_linkedin_certificationA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full behavioral burden. It only states the action 'add' without disclosing side effects, whether the operation is idempotent, authentication requirements, duplicate handling, or what happens after a successful add. For a mutation tool, this is a significant transparency gap.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with zero filler. It efficiently communicates the core action in 7 words, meeting the standard of every word earning its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 8 parameters, no output schema, and no annotations, the description is minimal. It covers the basic purpose, but omits behavioral context like expected return value, error scenarios, and prerequisites. The 100% parameter schema coverage compensates for missing parameter details, but overall completeness is merely adequate, not comprehensive.

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

  Parameters3/5

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

  Schema description coverage is 100%, so all 8 parameters already have descriptive text in the schema. The description adds no parameter-level meaning beyond the word 'certification', which aligns with the resource, but with full schema coverage a baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Add'), a clear resource ('certification'), and a target ('to your LinkedIn profile'). This clearly distinguishes it from sibling tools like delete_linkedin_certification, add_linkedin_skill, or add_linkedin_education, so an agent can immediately identify its function.

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

  Usage Guidelines3/5

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

  The description implies usage—when you want to add a certification—but gives no explicit contextual guidance, exclusions, or comparisons to alternatives such as add_linkedin_skill or add_linkedin_education. There is no 'when to use this vs. that' information, leaving the agent to infer the boundary from the resource name alone.

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

• generate_and_share_linkedin_postA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full behavioral disclosure burden. It reveals that the tool generates an image and shares a post, but it does not mention that sharing typically publishes publicly, whether a draft or confirmation is involved, or any permission/reversibility implications. This is a meaningful gap for a side-effecting tool.

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

  Conciseness5/5

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

  The description is a single clear sentence with no filler. It front-loads the main action (generate) and then states the follow-through (share), making it easy to scan and understand.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a two-step tool with no output schema and no annotations, the description is minimally sufficient but leaves gaps: it does not explain expected return values, failure behavior, or whether the post is published immediately. These omissions matter for an agent deciding how to confirm success.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline is 3. The description names Nano Banana as the image generator, which loosely relates to imagePrompt, but it adds no parameter-level guidance beyond what the schema already provides.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific action sequence—generate an AI image with Nano Banana and share a LinkedIn post with it—making the tool's purpose unmistakable. It also distinguishes this tool from the sibling share_linkedin_post, which presumably posts without generating an image.

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

  Usage Guidelines3/5

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

  The description implies this tool is for when a user wants both an AI-generated image and a LinkedIn post, but it does not explicitly contrast it with share_linkedin_post or state when not to use it. There are no exclusions or alternative routing, so the agent has to infer the appropriate context.

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

• delete_linkedin_positionA
  3.6/5.0
  Behavior2/5

  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 states that a position will be deleted but does not mention that the deletion is likely permanent, what the effect on the profile is, whether authorization scopes are required, or what happens after success or failure.

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

  Conciseness5/5

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

  The description is a single, front-loaded, zero-waste sentence. It states the exact action and target without any filler, which is ideal for a simple deletion tool.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with one well-described parameter, no nested objects, and no output schema, the description plus schema is largely sufficient for correct invocation. It lacks behavioral nuance such as irreversibility, but the core call context is complete.

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

  Parameters3/5

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

  The schema has 100% description coverage for the single 'positionId' parameter, so the structured data already fully documents the parameter. The tool description adds no parameter-specific information, but none is needed given the schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Delete') and a specific resource ('a position from your LinkedIn profile'), making the tool's purpose immediately clear. It is easily distinguished from sibling tools that delete skills, languages, education, or certifications.

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

  Usage Guidelines3/5

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

  The intended use is implied from the delete action and resource, but the description gives no explicit guidance about when to use this tool versus adding or updating a LinkedIn position. No alternatives or exclusions are mentioned.

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

• delete_linkedin_certificationA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral burden and does clearly identify the destructive operation ('Delete'). It does not mention permanence, irreversibility, or any account-level side effects, so it is minimally transparent rather than richly contextual.

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

  Conciseness5/5

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

  A single, front-loaded sentence with no filler. It conveys the operation and target clearly and earns its place without redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a single-parameter delete tool, the description plus schema cover the necessary call details. The main gaps are behavioral context (permanence) and explicit alternative routing, preventing a higher completeness score.

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

  Parameters3/5

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

  Schema description coverage is 100%: certificationId is already documented as 'The ID of the certification to delete.' The tool description adds no further meaning beyond this, so it meets the baseline but does not exceed it.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Delete') and resource ('a certification') and scopes it to the user's LinkedIn profile. This clearly distinguishes it from sibling delete tools for other resources and from add_linkedin_certification.

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

  Usage Guidelines3/5

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

  The action and resource imply the tool's use: when a certification should be removed from LinkedIn. However, it does not explicitly contrast with add_linkedin_certification or state when not to use it, leaving the guidance implicit rather than explicit.

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

• delete_linkedin_languageA
  3.7/5.0
  Behavior2/5

  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 states that the operation is destructive but does not mention irreversibility, authorization requirements, or any side effects on the LinkedIn profile, which is minimal for a mutation tool.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with no filler. Every word earns its place and the core action and target are immediately visible.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a one-parameter delete operation, the schema plus description is largely sufficient to invoke the tool correctly. However, the lack of annotations and the absence of any note about permanence or permissions leaves minor but real gaps for an agent deciding whether deletion is appropriate.

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

  Parameters3/5

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

  Schema description coverage is 100%, and the single parameter 'languageId' is already clearly described as 'The ID of the language to delete.' The tool description only adds profile context and does not need to restate what the schema already covers.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Delete') and a clear resource ('a language from your LinkedIn profile'). It is immediately distinguishable from sibling tools like add_linkedin_language and delete_linkedin_skill, which target different operations or resources.

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

  Usage Guidelines4/5

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

  The context is clear: this tool removes a language from the user's profile, while add_linkedin_language handles adding one and other delete_* tools target other profile sections. It stops short of explicitly naming alternatives or saying when not to use it, but the resource-specific phrasing makes the intended use obvious.

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

• get_linkedin_postsA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral burden. It adds useful scope context ('user's' and 'recent'), implying a read-only, date-recent retrieval. However, it does not disclose return format, ordering, pagination, authentication needs, or what exactly counts as 'recent'.

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

  Conciseness5/5

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

  The description is a single, focused sentence with no filler. It front-loads the action and resource and is easy to parse at a glance.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a one-parameter read-only tool with no output schema, this is minimally adequate: an agent can invoke it with just limit. But gaps remain around expected response structure, what 'recent' means, and whether additional authorization or pagination is involved.

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

  Parameters3/5

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

  Schema description coverage is 100%; the only parameter, limit, is already fully documented in the schema as 'Maximum number of posts to retrieve (default: 10)'. The description adds no additional parameter meaning, so the baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Get') and resource ('the user's recent LinkedIn posts'). It clearly distinguishes itself from sibling tools: no other LinkedIn sibling retrieves posts, and get_linkedin_profile/get_linkedin_connections target different resources.

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

  Usage Guidelines3/5

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

  The intended use is implied: call this when the user's recent LinkedIn posts are needed. However, the description provides no explicit when-to-use guidance, exclusions, or mention of alternatives, though no sibling directly overlaps with this function.

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

• delete_linkedin_publicationA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of disclosing behavior. It clearly states that a publication is deleted from the user's LinkedIn profile, which conveys the destructive nature. It does not mention irreversibility, permissions, or effects on the public profile, but the basic behavior is unambiguous.

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

  Conciseness5/5

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

  The description is one short, front-loaded sentence with no filler. Every word contributes to conveying the action and target.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a one-parameter delete operation, the description plus schema is nearly complete: it identifies the action, resource, and required ID. The main omissions are higher-level usage guidance and behavioral caveats, but the tool is simple enough that an agent can invoke it correctly with the provided information.

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

  Parameters3/5

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

  Schema coverage is 100% and the single parameter publicationId is already described as 'The ID of the publication to delete.' The description adds no additional meaning about how to obtain the ID or any format requirements, so the schema carries the weight.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names a specific action ('Delete'), a specific resource ('publication'), and its location ('from your LinkedIn profile'). This cleanly distinguishes it from sibling deletion tools for skills, positions, education, certifications, and languages.

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

  Usage Guidelines3/5

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

  The intended use is implied: use this tool when a publication should be removed from the profile. It does not explicitly state when not to use it or call out add_linkedin_publication as the complementary tool, but the verb makes the use case clear for this simple operation.

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

• get_linkedin_profileA
  3.8/5.0
  Behavior2/5

  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 reveals that the operation is a read ('Get') and scoped to the authenticated user, but it does not mention response shape, potential errors, authentication requirements beyond the implicit scope, or any limits. The description is accurate but minimally transparent.

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

  Conciseness5/5

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

  The entire description is one efficient sentence with no filler. The key verb, scope, and resource are all front-loaded, making it easy for an agent to parse quickly.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple, parameterless getter, the description provides enough information to know what the tool does and for whom. It lacks an explicit explanation of what 'profile information' includes, and there is no output schema to fill that gap, but the overall context is sufficient for basic tool selection and invocation.

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

  Parameters4/5

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

  The tool has zero parameters, so there is no parameter ambiguity to resolve. The schemas provide 100% coverage of the empty parameter set, and the description correctly focuses on the result rather than parameter details. Baseline 4 for a parameterless tool is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the action ('Get'), the resource ('LinkedIn profile information'), and the scope ('authenticated user's'). It is immediately distinguishable from siblings like get_linkedin_posts and get_linkedin_connections, which target different resources.

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

  Usage Guidelines3/5

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

  The phrase 'authenticated user's' implies this tool is for the caller's own profile, not for general people search. However, it never explicitly contrasts with search_linkedin_people or other profile-related siblings, leaving the routing decision mostly to inference.

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