hr

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

With no annotations, the description carries the full burden. It explicitly states that the server returns relevant data and the assistant forms the final output, which is an important behavioral disclosure about the tool's I/O contract. It does not discuss side effects or limitations, but being a question-answering tool, the disclosed behavior is sufficient.

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 compact and front-loaded with the core purpose, followed by examples and the data-flow note. The bilingual repetition takes a small extra space but is not wasteful and may aid multilingual agents.

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 two-parameter tool with no output schema, the description covers the purpose, the input type, and the expected behavior of the response. It is complete enough for an agent to know how to invoke it and what to do with the result, though it does not detail the exact format of the returned data.

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 is 3. The description adds semantic context about the type of question expected (specific, experience-focused, with examples), but it does not add much beyond what the schema already states for the question and candidate parameters.

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

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

The description clearly identifies the tool as one that asks a specific, targeted question about a candidate's experience, with concrete examples ('работал ли с X?', 'что делал в Y?'). This separates it from static retrieval tools like get_resume or get_profile and also distinguishes it from assessment or manage_interview by focusing on a pointed Q&A interaction.

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

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

The description provides clear context: use when you need a specific answer about a candidate's background rather than a full document or profile. It lacks explicit exclusions or direct sibling comparisons, but the examples and phrasing imply the appropriate situation for use.

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

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It explains the main workflow: send creates an assessment and the candidate uploads a solution file; status returns status and a download link. It omits side effects, permission requirements, and any limits or caveats, so transparency is only partial.

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 compact and front-loaded with the action dispatch and required parameters. It contains no filler, and the brief bilingual phrasing is reasonable for the context. Every sentence contributes to understanding.

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

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

For a dual-action tool with no output schema or annotations, the description covers the essential operations and their parameter requirements. It does not explicitly state that send returns assessmentId for later status checks, though the schema hints at it. Overall, it is sufficiently complete for a straightforward 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?

The schema already covers all 7 parameters with descriptions, so the baseline is 3. The description adds value by grouping parameters by action and indicating which are required for send versus status, which is not immediately obvious from the schema alone.

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

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

The description explicitly names both actions of the tool: sending a take-home assessment and checking its status/download link. This makes the tool's purpose concrete and distinguishes it from sibling tools like send_vacancy or message_candidate, which deal with different workflows.

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

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

The description gives clear per-action usage conditions: send requires title, body, recruiterContact, while status requires assessmentId. It also mentions the candidate's file upload flow. However, it does not explicitly state when to prefer this tool over sibling alternatives or when not to use it.

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

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. It discloses the scope of the returned data (salary components, notice period, work format, visa, relocation) and the language default, but it does not mention side effects, error behavior, or permissions. The 'get' verb implies a read operation, but that is not explicitly stated.

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 compact and front-loads the tool's purpose with a concrete list of returned terms. The bilingual duplication is slightly redundant but still efficient and unlikely to confuse an agent.

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 low complexity, full schema coverage, and simple 2-parameter input, the description sufficiently explains what data is returned and acknowledges language options. It is not fully complete because it lacks explicit usage guidance and behavioral notes, but nothing critical is missing for basic invocation.

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

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

Schema description coverage is 100%, so the schema already documents both lang and candidate. The description repeats the lang default and adds the candidate slug context only indirectly; it does not add meaningful semantics beyond the 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 clearly states this tool retrieves the candidate's terms for joining: compensation expectations, notice period, work format, location, visa, and relocation. This specific field list distinguishes it from sibling tools like get_profile or get_resume, so an agent can tell them apart without opening schemas.

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 usage context is implied by the content: use this when you need a candidate's employment conditions such as salary expectations or notice period. However, it does not explicitly state when to prefer this over alternatives or provide exclusions, leaving the agent to infer routing from the sibling list.

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 a key behavioral trait: contacts are gated behind the recruiter_context introduction, which is beyond what any annotation would provide. It also implies the tool returns sensitive contact data, adding important context for the agent. Since there are no annotations, the description carries the full burden and handles it well.

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: it states what the tool returns first, then the prerequisite, and then the parameter caveat. Every sentence earns its place, and the bilingual format is efficient for the target audience.

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 optional parameter, no output schema), the description covers the essential points: what it returns, the prerequisite, and the parameter semantics. The only minor gap is that it does not mention whether the output format varies by communication channel, but this is not necessary for a simple contact-lookup 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%, so the baseline is 3. The description adds minimal parameter-specific explanation beyond the schema, but the schema itself already fully documents the candidate parameter, including the slug source and the optionality in personal mode. Thus, the description meets the baseline without needing to compensate.

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: 'Прямые контакты кандидата (телефон, email, мессенджеры)' (Direct contacts of the candidate: phone, email, messengers), using a specific verb and resource. It also adds a critical prerequisite: contacts are only provided after introducing yourself via recruiter_context, which clearly distinguishes this tool from others.

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

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

The description explicitly states when to use this tool: after introducing yourself via recruiter_context. It also mentions the alternative context (personal mode) where the candidate parameter is optional. However, it does not explicitly name sibling tools or provide a 'when not to use' clause, so a half-point deduction is applied.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what content is returned and gives no guidance on side effects, default language behavior, candidate resolution, auth needs, or output format.

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 short and front-loaded with the core purpose and usage hint. The bilingual repetition is slightly redundant but not wasteful enough to penalize heavily.

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 two-optional-parameter lookup, the description conveys the main purpose and when to use it. However, with no annotations and no output schema, it does not clarify default behavior when lang or candidate are null, or what the returned answers look like.

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%, and the schema already documents lang with allowed values and candidate as a slug from search_candidates, including the personal-mode caveat. The description adds no parameter-level meaning beyond its general purpose, so the baseline 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 identifies the tool as retrieving a candidate's answers to common recruiter questions, and it names the specific resource (candidate FAQ). It does not explicitly contrast itself with sibling get_* tools, but the meaning is distinct enough.

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

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

The phrase 'check here before writing to him' gives a concrete trigger for when to call this tool. It does not mention exclusions or alternatives, but the context is clear and actionable.

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

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

No annotations are provided, so the description carries the full burden. It discloses what the tool returns (name, city, summary, links) and language behavior, but it does not explicitly state that this is a safe read-only operation or describe output formatting or errors. For a simple getter, this is adequate but not deeply transparent.

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 compact and front-loaded, stating the profile contents first and then usage notes. The bilingual repetition adds some redundancy but is arguably useful for multilingual agents. Every sentence contributes meaningful information.

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

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

With no output schema, the description compensates by enumerating the returned fields: name, city, summary, and links. It also covers language selection and positions the tool as the starting point. It does not describe error cases or edge conditions, but for a simple profile tool the provided context is largely sufficient.

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 schema already documents both parameters. The description adds the lang default behavior (ru) and implies the candidate slug concept, but mostly repeats what the schema already provides. No significant new parameter meaning is added beyond the 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 clearly identifies the tool as a candidate profile overview listing name, city, summary, and links. It differentiates itself from siblings like get_resume and get_contacts by enumerating specific profile contents, though it does not 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 phrase 'Start your acquaintance here' provides clear entry-point context, and it specifies the language default behavior (ru by default or en). It does not explicitly state when not to use this tool or name alternative tools, but the context is clear enough for a simple profile lookup.

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

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

With no annotations, the description carries the full burden. It discloses that references come with the consent of former colleagues and managers, which is useful behavioral context, but it does not state whether this operation is read-only, whether any external parties are contacted, or what side effects might occur. The 'get' prefix implies reading, but the description itself is moderately informative.

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 short, front-loaded with the core meaning, and adds a purpose signal. The Russian and English versions repeat the same information, which is slightly redundant but not harmful, so it earns a 4 rather than a 5.

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 and no output schema, the description explains what the tool returns and when to use it. It could mention output format or empty-reference behavior, but the core information needed for correct invocation is present.

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 single `candidate` parameter is already documented in the schema. The description adds no additional meaning about how the parameter should be used, which keeps this at the baseline 3 rather than higher.

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

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

The description clearly identifies the tool as returning references about a candidate from former colleagues and managers, giving a specific resource and content type. It also frames it as a trust signal before an offer, which distinguishes it from siblings like get_profile, get_resume, and get_contacts.

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

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

The phrase 'trust-сигнал перед офером' explicitly indicates when to use this tool: before making an offer. It does not name alternatives or exclusions, but the timing context is clear enough for an agent to select it appropriately among the listed siblings.

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

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

No annotations are provided, so the description carries the behavioral disclosure burden. It conveys that the tool returns resume content and implies a read-only operation, but it does not explicitly describe return behavior, side effects, authentication needs, or other runtime traits. This is adequate for a simple get-style tool but not rich.

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 short, front-loaded with the core content, and ends with a practical usage hint. The bilingual duplication is slightly redundant but still compact and purposeful given the audience.

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 retrieval tool with two optional, fully documented parameters and no output schema, the description gives a solid sense of what the agent will get and when to start with it. It could be stronger with explicit alternative routing, but nothing critical is missing.

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

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

Schema description coverage is 100%, with both resumeId and candidate already well documented including defaults, sources, and optionality. The description adds no parameter-level detail, so the baseline score of 3 applies 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.

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

The description clearly identifies the resource as the full candidate resume and enumerates its contents: work history, achievements, skills. It also positions itself as the starting point for a comprehensive view, distinguishing it from narrower sibling tools such as get_contacts or get_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?

The phrase 'Начните отсюда, если нужна полная картина / Start here if you need the full picture' provides clear context for when to use this tool. However, it does not explicitly name alternatives or state when not to use it, so it stops short of full exclusionary 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state meaningful side effects: propose offers slots, reschedule replaces slots, and cancel revokes an invitation. However, it does not disclose permissions, persistence effects, notifications, or what happens after a successful action.

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 compact, well-organized around action= segments, and front-loaded with the core purpose. The bilingual summary in English is slightly redundant with the Russian text but does not significantly hurt readability.

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 an 11-parameter tool with three distinct action modes and no output schema, the description provides sufficient high-level routing and conditional parameter requirements. Combined with the rich 100% schema descriptions, an agent can construct a valid call, though it lacks clarification around output behavior or error cases.

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 baseline is 3. The description adds value by mapping each action to the required parameter set (e.g., reschedule needs conversationId and proposedSlots; cancel needs conversationId) and by specifying the ISO-8601 UTC format for slots, which is not fully captured in every parameter schema description.

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

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

The description states a precise operation on a specific resource: propose, reschedule, or cancel an interview with the candidate. It lists the three action modes explicitly, which makes the tool clearly distinguishable from siblings like message_candidate or send_vacancy.

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

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

The description explains what each action does and which parameters are needed, but it gives no explicit guidance on when to prefer this tool over alternatives or when not to use it. Sibling tools are not referenced, and no exclusion conditions are 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?

There are no annotations, so the description carries the burden. It does disclose that the tool is an evaluative call and lists the structure of the returned assessment. It does not mention side effects, permissions, or limitations beyond the schema, leaving some ambiguity around how candidate context is resolved.

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 compact bilingual sentence with the action and key output components front-loaded. It could split the two languages for clarity, but there is no dead weight.

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 no output schema, the description names the main output fields, which helps. However, it does not clarify whether a candidate must be selected in context or passed via candidate, and 'условия выхода' is ambiguous. The schema compensates for parameter details, but not for candidate-resolution behavior.

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 schema already documents lang, candidate, and vacancyText. The description adds no parameter-level information beyond pointing at the vacancy text; baseline 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 names a concrete action (paste a job description) and a concrete outcome (structured candidate-fit assessment with matched skills, seniority, exit conditions). This is enough to distinguish match_vacancy from siblings like get_resume or send_vacancy.

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 use case is implied by 'evaluate candidate fit', but the description gives no explicit guidance about when to choose this tool over sibling tools such as assessment or ask_about_experience, nor does it state exclusions or prerequisites.

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

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

With no annotations, the description carries the full burden and does disclose the key side effect that sending a message lets the candidate reply in messenger. However, it does not mention other behavioral factors such as permissions, external send effects, or the requirement to provide subject and recruiterContact when opening a new thread, leaving some transparency gaps.

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

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

The description is two short sentences with the mode behavior front-loaded and an English summary for accessibility. Every word contributes to understanding the tool without redundant filler.

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

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

For a tool with three modes and no annotations, the description covers the core dispatch rules and the async reply behavior. It relies on the rich 100%-covered schema for parameter requirements like subject/recruiterContact, and it does not describe return values since there is no output schema; these are minor gaps rather than blockers.

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 covers all five parameters with descriptions, so the baseline is 3. The description adds value by specifying the parameter-combination logic (absence of text/conversationId = list, conversationId = history, text = send), which is not fully captured by any single schema field.

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

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

The description clearly identifies the tool's purpose as messaging with a candidate and enumerates three specific actions: listing threads, reading a thread history, and sending a message. This disambiguates it from sibling tools like send_vacancy or ask_about_experience because it owns the candidate-correspondence domain.

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

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

It gives explicit mode-selection rules based on parameter presence: no text/conversationId lists threads, conversationId reads history, text sends a message. This is clear context, though it does not explicitly name sibling tools or state when not to use this tool in favor of an alternative.

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

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

With no annotations provided, the description carries the behavioral burden. It discloses that the candidate will see who is interested, that contact access becomes unlocked, and that the email must be the one used to log in. It does not address reversibility or persistence, but the key side effects are clearly surfaced.

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 short and front-loaded, leading with the core action and immediate benefit. The English clause is a faithful restatement of the Russian sentence rather than new content, creating minor redundancy but no meaningful bloat.

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 six-parameter tool with full schema descriptions and no output schema, the description covers the essential context: what the tool does, what the candidate perceives, and what access is unlocked. The main omission is any statement about the return value, which is a minor gap for a setup-style action.

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 baseline is 3. The description adds valuable semantic nuance beyond the schema: email must be the account you logged in with, and company/name/role together form the identity shown to the candidate.

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

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

The description states a specific verb-resource pair: introduce yourself and unlock recruiter context/contacts. It also clearly references the sibling tool get_contacts as the outcome, making it easy for an agent to distinguish this setup action from the contact-fetching tool.

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 frames the tool as a prerequisite for get_contacts: 'вам откроются контакты (get_contacts)' tells the agent when to invoke it. It does not explicitly say when not to use it or describe alternative paths, so it falls just short of full 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?

With no annotations provided, the description carries the burden of disclosing behavior. It states that the candidate receives a notification and can respond, and clarifies the fallback behavior for recruiterContact. It does not discuss reversibility or required permissions, but the core side effect of sending a vacancy is clear.

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 front-loaded with the main purpose, then gives concise optionality guidance. The bilingual closing sentence is slightly redundant with the Russian details, but the overall length is appropriate and every part contributes useful context.

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 6-parameter tool with no annotations and no output schema, the description provides enough invocation context: purpose, condition for use, and key fallback behavior. It appropriately relies on the 100%-covered schema for parameter details, though it does not describe the response format.

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 is 3. The description adds value by explaining that candidate can be omitted in personal mode and that recruiterContact will fall back to the user's email, which is more meaningful than the schema's field-level descriptions.

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

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

The description clearly states the action: send a vacancy to a candidate, and frames it as the first step when the candidate is suitable. This distinguishes it from generic messaging tools like message_candidate by naming the specific resource being sent.

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

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

The description gives explicit when-to-use guidance: 'first step if the candidate fits.' It also explains mode-specific behavior, noting that candidate is unnecessary in personal mode and recruiterContact defaults to the authenticated email. It does not name alternative tools or exclusion conditions, but the context is sufficient for selection.

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