Wiser Human Agent Escalation Line

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

Beyond the annotations, it discloses two behaviors that matter: the automated assessment is re-run and updated as a side effect, and this is rate-limited ('a limited number of times per case'). It also flags credential sourcing (case_id/case_token from submit_escalation). It doesn't say what happens when the limit is hit or whether addenda accumulate, so not a 5.

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, front-loaded with the action and followed by the side-effect and prerequisites. The mid-sentence enumeration is slightly long but each item clarifies what can be added.

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 4-parameter mutation tool with no output schema, the description covers the action, the side effect, the rate limit, and where the required credentials come from, and routes the agent to check_escalation for output. It does not contradict the non-readOnly, non-idempotent, non-destructive annotations.

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 every parameter including the nonce is already documented. The description only reinforces the credential provenance (from submit_escalation) and hints at the message content, which is a baseline-level addition rather than new detail.

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?

Specific verb+resource ('Add information to an escalation case') with a concrete enumeration of what counts as information (decisions, principal replies, contact details, team requests). It clearly distinguishes itself from submit_escalation (creates the case) and check_escalation (reads the assessment).

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?

Gives clear context for when to use it — after a case exists — and points to check_escalation for reading results and submit_escalation as the source of the required credentials. It omits an explicit 'do not use when' condition, but the case-scoped framing is sufficient for correct routing.

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

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses expected latencies (assessment ready within 6 minutes, human replies usually within 2 hours), that replies are surfaced only through this tool, and that credentials are required. These are exactly the behavioral traits an agent needs to decide when to poll and when to stop.

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 what the tool returns, followed by timing expectations and credentials. Every sentence carries useful information, and there is no redundant or vague wording.

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 read-only polling tool with no output schema, the description adequately covers return contents, timing, and credential requirements. A minor gap is the absence of guidance on error or expired-token behavior, but an agent has enough to invoke it 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 description coverage is 100%, so the schema already documents case_id, case_token, and nonce in detail. The description only reinforces that case_id and case_token originate from submit_escalation, adding little beyond the structured fields. This matches the baseline 3 for a fully documented schema.

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

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

The description states a specific verb and resource ('Check an escalation case you opened') and enumerates what is returned: status, automated assessment, and replies from the Wiser Human team. This clearly distinguishes it from submit_escalation and add_to_escalation, which create and append to a case rather than read it.

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 concrete guidance on repeat usage: replies appear only here, so poll again until a human replies or the principal decides. It also states the prerequisite that case_id and case_token come from submit_escalation. It stops short of naming explicit alternatives or when not to use it, keeping it at 4 rather than 5.

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?

Goes well beyond the annotations: it discloses the synchronous accept/reject reply, an automated assessment within ~1-6 minutes, human review of every case with ~2 hour replies, and that human replies appear only on the case so the agent must poll again. It also adds a privacy constraint (no credentials or secrets) and an instruction to retain case_id and case_token. The gap is that with idempotentHint=false it never warns that repeated submissions create duplicate cases, nor does it explain how the sibling add_to_escalation relates to this call.

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?

Front-loads the eligibility conditions and follows with the service behavior, which is the right order for an agent deciding whether to call. Nearly every sentence carries information, though the final sentence crams several unrelated submission constraints together and could be split for scanability.

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, non-idempotent submission tool with no output schema, the description covers the important unknowns: what the reply means, how long each stage takes, and that results must be polled. What is missing is the duplicate-case consequence of resubmitting and any mention of the add_to_escalation sibling, both of which an agent needs to use this tool correctly across multiple turns.

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 and the schema already documents every field including length bounds. The description adds some real meaning beyond it — write in plain English, describe the conflict in general terms, exclude credentials and secrets — but restates the summary/situation length floors that the schema already specifies and says nothing about nonce, targets, deadline, or options_considered.

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

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

States a specific verb and named service ('Get help from the Wiser Human Agent Escalation Line') and immediately frames the resource as an escalation channel for blocked agents. It distinguishes itself from the sibling check_escalation by describing that tool as the read path for results, so an agent can route between them without opening either schema.

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?

Gives three explicit triggering conditions (blocked from needed information and tempted to circumvent, unsure whether a target is real before a harmful action, defect or contradiction blocking legitimate completion) plus a precondition ('cannot reach your principal in time'). It also names the follow-up step (call check_escalation) and its timing, which is the closest thing to an alternative in this tool set.

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