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

With annotations already declaring destructive/openWorld/non-idempotent, the description still adds substantial context: the worker has its own bash and file read/write tools, runs against the signed-in Perch plan, and permission=take_the_wheel means it never asks before writes or commands. It also discloses the return shape and the job_id escape hatch, which is exactly the kind of behavioral detail annotations cannot carry.

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-loaded with the action and the execution model, then the guidelines flag, then the long-running flow — a sensible order with little filler. Minor redundancy: the guideline contents are listed in both the description and the guidelines parameter's schema text.

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 open-world delegating tool with no output schema, the description covers the execution model, permission implications, billing surface, return values, and the async continuation path. Nothing an agent needs in order to call it correctly is missing, and secondary params (model, effort, persona) are fully documented in the schema.

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, but the description earns above that by tying two parameters to an workflow: guidelines toggles the prepended guideline block and wait_seconds bounds blocking before a job_id is returned. That causal link is not spelled out in the schema itself.

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 resource ("Delegate a task to Perch AI (worker agent) via the official perch CLI") and immediately characterizes the resource: it runs autonomously in a working directory with its own tools. That framing distinguishes it from the sibling polling/status tools, which the description also names.

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 concrete operational guidance: use wait_seconds to bound blocking on long tasks, and poll perch_job_status when a job_id comes back; also explains that guidelines:false disables the prepended guidelines. It stops short of saying when not to delegate (e.g., trivial work better handled inline) or when perch_status beats this tool.

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 annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the risk profile is known. The description adds one genuinely useful behavioral detail beyond them: cancellation kills the whole process tree, not just the job record. It does not say whether the call errors on a completed job or whether it waits for termination, and idempotentHint=true is left unexplained.

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?

A single front-loaded sentence with zero filler; the action and target come first and the parenthetical scope detail is placed right where it is needed.

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 destructive, no-output-schema tool with an undocumented parameter, the description is thin: no return behavior, no handling of already-finished or nonexistent jobs, no source for job_id, and no note that repeated calls are safe despite idempotentHint=true.

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 single parameter has 0% schema description coverage (just a string with minLength 1), so the description carries the full burden and says nothing about job_id. It does not state where a job_id comes from (presumably the delegate_to_perch response) or whether a name or prefix could be passed.

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?

"Kill a running delegated Perch job" gives a specific verb (kill) and a specific resource (a delegated Perch job), and "(process tree)" scopes what kill means. It is clearly distinguishable from the sibling status/delegate tools, though it never names them explicitly.

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?

There is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives such as checking perch_job_status first. The only guidance is implied by the word "running," which hints the job must be active, but nothing says what happens if it already finished.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds modest value by indicating the call returns both status and, once ready, the result, but says nothing about whether results expire, whether polling is required, or what terminal states exist.

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?

A single sentence, front-loaded with the verb and resource, with no filler or redundancy. It is efficient, though efficiency here comes partly from under-specification rather than tight editing.

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 one required parameter, no output schema and no result-format documentation, the description does far too little: it never describes what a 'status' value looks like, whether the call is safe to poll repeatedly (though annotations imply idempotence), or how it relates to perch_job_cancel. The annotations carry the safety story, but the return semantics remain unexplained.

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 0% and the description only restates the parameter name ('by job_id') without format, provenance, or validation details. Since the sole input is required, the description should clarify where the job_id comes from (presumably delegate_to_perch) and that it is not a job name or index.

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 specific verb+resource pair ('Get status/result of a delegated Perch job') and ties it to a job_id, so the agent knows exactly what the tool returns. It stops short of differentiating itself from the sibling perch_status, leaving the boundary between the two ambiguous.

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?

There is no explicit guidance on when to use this versus perch_status or perch_job_cancel, both of which are plausibly relevant to a non-terminal job. The phrase 'delegated Perch job' hints that it follows delegate_to_perch, but that is inference rather than stated 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?

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds genuinely new context: the check runs locally and costs no model call, which is the key operational fact for an agent deciding whether to probe first.

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 tight clauses: what it returns, then when to call it. The cost note ('no model call') is front-loaded alongside the capability, and no sentence is wasted.

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-param, no-output-schema probe, the description covers what is inspected and when to use it. It stops short of describing the result shape or what state means 'not ready' (e.g., whether an unsigned CLI is a hard blocker), which would fully close the loop for an agent gating a delegation.

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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the schema is empty and fully consistent with 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?

States precisely what the tool reports: perch CLI presence, sign-in state, and this server's live job list. That enumeration of returned facts distinguishes it from perch_job_status (single-job) and delegate_to_perch (work dispatch) without needing the 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?

Gives an explicit call condition — 'Call before delegating if unsure the worker is ready' — which ties it directly to delegate_to_perch. It does not state when to skip it (e.g., if readiness is already known), so it stops short of full when/when-not guidance.

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