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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so this is a read-only deterministic lookup. The description adds genuinely useful context beyond that: matching is deterministic alias-based rather than generative, guardrails are derived from negated phrases in the input, and a bundle URL comes back. It stops short of saying what happens when no alias matches.

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 dense sentence with zero filler, front-loading the input-to-output transformation before the secondary outputs. Every clause (alias match, negated phrases, bundle URL) carries distinct 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?

For a one-parameter read-only tool with rich annotations, the description covers the input meaning, the matching method, and the shape of the return (ids, guardrails, bundle URL) even without an output schema. The remaining gap is failure semantics — no match, partial match, or multiple matches — which an agent would need before relying on it.

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?

With one parameter and 100% schema description coverage (including an inline example), the schema already does the work, so 3 is the baseline. The description does add one small signal the schema lacks — that the task string may contain negated phrases which become guardrails — but it gives no guidance on phrasing a good multi-job 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 a concrete transformation: a multi-job task description becomes existing JTBD ids, with a deterministic alias-match mechanism, plus guardrails and a bundle URL. That is specific verb+resource behavior. However, it never distinguishes itself from the sibling 'stack_delta', which an agent could plausibly confuse with it, and the name 'stack' alone carries none of this meaning.

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 'multi-job task description' implies the input precondition for calling this, and describing the output as 'existing JTBD ids' hints it is a lookup against a known catalog rather than free generation. But there is no explicit when-to-use, no when-not-to-use, and no mention of stack_delta, bundle, or search as alternatives.

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