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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: result cardinality (up to six rules), provenance (quoted from the pinned release, with source), and a conditional behavioral branch ('with a token, event resume also returns a goal block').

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 trigger condition and followed by the return behavior; almost every clause conveys new information. The parenthetical examples are compact and useful rather than decorative.

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?

With five optional parameters, no output schema, and low schema coverage, the definition supplies the return shape (quoted rules plus source) and the token/resume special case, which is the key thing an output schema would otherwise carry. The remaining gap is argument-combination rules and the meaning of the stage enum, which are not covered anywhere.

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 only 20%, so the description must carry meaning, and it partly does: it exemplifies event ('blocked'), an example module ('nobrainer-review'), and explains topic pr_dod as gates and verdict for a PR's Definition of Done, plus token's role in the resume goal block. It says nothing about `stage` values, and critically nothing about how parameters combine — whether they are mutually exclusive, whether multiple may be supplied, or what an argument-free call returns.

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 concrete retrieval behavior — returning up to six rules quoted from a pinned release, with their source — and enumerates the domains it covers (stage, event, module, PR Definition of Done). It is not a pure restatement of the name/title, though the title ('Get the next Flow step') implies workflow advancement while the body describes a reference lookup, a slight framing mismatch an agent must reconcile.

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?

'Use when you need guidance on a Flow stage, an event (e.g. blocked), a module (e.g. nobrainer-review), or a PR's Definition of Done' gives clear trigger conditions with examples. It offers no exclusions or named alternatives among siblings (check_flow_done, check_flow_evidence, start_flow_task), so the agent gets context but no routing away from lookalike tools.

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