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 clearly frames the tool as a read-only extraction operation and lists what gets extracted, which is useful. However, it does not disclose potential failure modes, network dependency, output format, or error behavior, leaving some behavioral ambiguity.

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

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

Two short sentences, no filler. The first sentence front-loads the action and extracted fields, and the second explains the purpose. Every word earns its place.

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

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

For a two-parameter tool with no output schema and no annotations, the description provides the key information: what is extracted and why it is used. It stops short of specifying the exact return shape or handling of invalid links, but the listed fields and the register_posting connection cover most of what an agent needs for correct 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 baseline is 3. The description adds context about what the extracted data is used for, but it does not add parameter-specific meaning beyond the schema's existing descriptions for 'site' and 'link'.

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

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

The description uses a specific verb ('추출합니다' – extracts) and names the resource (job posting detail page) plus the exact fields extracted: 주요업무/자격요건/우대사항/마감일/근무지. It also explicitly ties the tool to register_posting, which distinguishes it from siblings like search_jobs and send_collection_summary.

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 a clear trigger condition: 'register_posting에 넘길 입력을 만들 때 사용합니다' (use when creating input to pass to register_posting). It does not explicitly enumerate when not to use it or name alternative tools, but the stated use case is enough for an agent to route correctly 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?

With no annotations provided, the description carries the full burden. It discloses the deduplication behavior (skip if link already exists, with an exception for '마감' status), that created_at is auto-recorded, that no Discord notification is sent per call, and that the tool returns JSON. These are important behavioral traits beyond what a schema would show. It does not mention error handling or permissions, but for a registration tool, the covered aspects are 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 a single paragraph of about 4 sentences, efficient and front-loaded with the primary purpose. It includes crucial operational notes (dedup rule, auto-timestamp, notification batching) without unnecessary filler. It is concise while conveying all key behavioral guidance.

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

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

Given the tool's complexity (17 params, no output schema), the description covers the essential context: what the tool does, dedup logic, auto-created_at, the JSON return and the recommendation to batch and call send_collection_summary. It does not explain the exact JSON structure or error cases, but those are not critical for correct invocation, and the schema handles parameter details. Overall, it provides enough for an agent to use the tool correctly.

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

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

Schema coverage is 71% (12 of 17 params have descriptions). The description itself adds little beyond the schema: it reinforces that 'link' is the dedup key (already stated in schema) and explains the intended flow of collecting results. Since the schema already documents most parameters in detail, the description does not need to repeat them. It adds marginal value but does not compensate for the few undocumented params.

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 purpose: registering collected postings into a specific Notion DB ('🗃️ 공고 분석'). It uses a specific verb ('등록합니다'), names the resource, and explains the deduplication rule. It is distinct from siblings like search_jobs and get_job_detail, which are for retrieval, and send_collection_summary, which is for final notification.

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 implicitly indicates when to use this tool: when you have collected postings to register. It also explicitly instructs to accumulate results and call send_collection_summary only once at the end, rather than sending per-call notifications. However, it does not contrast with search/get tools, but that is obvious given the verb. It provides clear operational guidance for the calling pattern.

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 the tool uses Playwright automation and only supports two sites, and it notes the alternative for other sites. However, it doesn't specify error behavior if an unsupported site is passed (e.g., returns empty, throws error), which is a minor gap.

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

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

Two sentences, zero waste. The first sentence states purpose and output; the second addresses limitations and alternatives. Front-loaded and efficient.

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?

No output schema exists, so the description must cover return values, which it does (list of title, company, link). It also covers the key limitation (supported sites) and the alternative path. It doesn't mention pagination or timeouts, but those are minor given the schema covers limit.

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 all parameters. The description adds no additional parameter-specific meaning beyond the schema, so the baseline of 3 applies.

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

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

The description clearly states the verb (search), the resource (job postings on job sites), and the output format ([title, company, link]). It also differentiates from siblings like get_job_detail and register_posting by focusing on searching. The explicit list of supported sites adds specificity.

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 (only for linkareer and jumpit) and when not to (for automated-blocked sites like Wanted/Saramin, use mcp__claude-in-chrome instead). It also references documentation, giving clear routing 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 behavioral disclosure. It reveals the external side effect (sends to Discord) and notes that it batches results into one message rather than sending individual messages. However, it does not mention what happens on webhook failure, idempotency, or any rate-limit implications, leaving some gaps for a side-effect tool.

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, dense sentence that front-loads the purpose and usage. It packs a lot of relevant detail (what is aggregated, the delivery channel, and when to call) without extraneous words. It could be slightly more scannable, but it is appropriately sized for the tool.

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 batch summary sender, the description covers the essential operational context: what inputs it expects, how to invoke it, and what it produces. The only missing aspects are error-handling details (e.g., webhook failure) and any output confirmation, but given this is a fire-and-forget notification tool with no output schema, these are minor and do not impede correct usage.

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

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

The schema already describes all five parameters at 100% coverage, so the baseline is 3. The description adds meaningful context beyond this: it explains that `results` is the ordered array of JSON outputs from each register_posting call, and it specifies that `reviewedCount` defaults to `results.length + excludedByCondition` when omitted. This extra semantic clarification earns a 4.

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 is explicit: it aggregates register_posting results, organizes them into tier status, new options, and review items, and sends a single summary via Discord webhook. This clearly distinguishes it from siblings like search_jobs, get_job_detail, and register_posting by stating the specific resource (collection batch results) and action (report via webhook).

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

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

The description provides a clear directive: call it only once after completing multiple registrations, implying it should not be called per registration. It does not explicitly state alternatives or exclusions, but the context makes it obvious this is the final reporting step, so the guidance is sufficient.

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