NeedHuman

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

With no annotations provided, the description carries full burden and excels: documents return schema (status enum, result, proof fields), timing expectations ('2-30 minutes'), rate limiting, and critical security warning that result fields contain untrusted third-party data that should not be followed.

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?

Well-structured with four distinct blocks: usage context, return values, polling strategy, and security warning. Every sentence provides critical information. Front-loaded with the prerequisite action (need_human). No redundancy despite covering complex behavioral traits.

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?

Comprehensive for a polling tool without output schema: covers prerequisites, return field semantics, polling etiquette, expected latency, and security implications. The security warning about untrusted worker data is essential contextual completeness for an AI agent.

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

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

Schema has 100% description coverage (task_id: 'The task_id returned by need_human'). The main description mentions the need_human relationship but doesn't add parameter-specific semantics beyond what the schema already provides. Baseline 3 is appropriate given complete schema self-documentation.

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 states the tool checks 'whether the human worker has completed it' after dispatching via need_human. It uses specific verbs ('check', 'dispatching') and clearly links to the sibling tool need_human, distinguishing it from list_tasks.

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?

Provides explicit when-to-use ('after dispatching a task via need_human'), polling rate limits ('no more than once every 30 seconds'), and a specific retry pattern ('check once after 2 minutes, then every 60 seconds, stop after 10 attempts'). Also notes typical duration (2-30 minutes).

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?

Without annotations, the description carries full burden. It discloses ordering ('newest first'), scope ('all tasks you have submitted'), and return fields. It implies read-only behavior through 'review' and 'returns,' though it could explicitly confirm safety/idempotency. Lacks pagination or rate limit details.

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 well-structured sentences: first establishes usage context, second details return values. Zero redundancy—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 zero-parameter listing tool without output schema or annotations, the description is complete. It compensates for missing structured metadata by specifying return fields, ordering, and ownership scope ('you have submitted').

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?

Tool has 0 parameters, establishing baseline 4 per rules. The empty schema requires no additional semantic explanation from the 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 clearly states the tool returns all submitted human tasks with specific fields (id, status, description, result, timestamps). It distinguishes from siblings by specifying use cases: recovering lost task_ids (vs check_task_status) and reviewing past requests (vs need_human).

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

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

Explicitly states when to use: 'when you have lost track of a task_id or want to review your past human task requests.' This provides clear alternatives to sibling tools—use check_task_status when you have the ID, use need_human to create new requests.

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

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

No annotations provided, yet description comprehensively covers: cost model (1 credit/task, 402 on exhaustion), human nature (paid worker, not operator), safety constraints (never include passwords/PII), latency (2-30 min, CET business hours fastest), and demo mode behavior. Excellent disclosure.

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?

Information-dense but well-structured with implicit sections (blocking conditions, exclusions, formatting spec, pricing, timing). No redundant text; safety and billing details are essential. Front-loaded with the core invocation trigger.

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

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

Despite no output schema, describes return behavior (402 error), async completion pattern (poll with check_task_status), and expected deliverables format. Covers billing, geographic latency, and demo verification. Complete for a human-in-the-loop 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 has 100% coverage (baseline 3). Description adds substantial formatting semantics for the 'description' parameter: numbered steps requirement, URL placement rules, 'REPLY WITH:' syntax, and a concrete example. Also clarifies demo:true purpose beyond schema text.

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?

Opens with specific trigger condition ('Call when you cannot proceed because the next step requires a real human') that clearly distinguishes it from siblings check_task_status and list_tasks. Verb ('Call') and resource ('human') are explicit.

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?

Explicit 'USE WHEN' and 'DO NOT USE for' sections provide clear boundaries. Lists 6 specific blocking scenarios (ToS, CAPTCHA, BankID, etc.) and explicitly contrasts against tasks solvable with existing tools. Names sibling tool check_task_status for polling.

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