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

The description goes far beyond annotations, revealing probe inheritance, error conditions, the implication that 'probeSpec alone implies post-deploy', 'pre-merge drops the probe', and linter behavior differing by mode. It also states the return payload. There is no contradiction with the annotations.

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 information-dense but run-on with semicolons and nested clauses. Every clause earns its place and the core purpose is front-loaded, but breaking it into shorter sentences would improve parseability.

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 no output schema, it explicitly states return values ('Returns updated criterion details (text, probeClass, probeSpec) and any quality findings'), an error case ('error=probe_required'), and mode-specific constraints. It covers the necessary behavioral surface for an agent to call 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?

Although the schema covers property names and types, the description adds crucial cross-field semantics: probeClass=post-deploy requires probeSpec, an omitted probeSpec is kept from an existing criterion, probeClass=pre-merge drops the probe, and probeSpec alone implies post-deploy. This is exactly the meaning an agent needs beyond the 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 ('Update') and resource ('acceptance criterion') and enumerates what can be changed: 'its text and/or its class + probe'. This clearly distinguishes it from siblings like goal-add-criterion and goal-remove-criterion, even though those alternatives are not explicitly named.

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 description gives clear mode-dependent guidance: 'Grove mode: only while goal is in backlog (frozen once started)' and 'Standard mode: until goal is done'. It does not explicitly mention alternative sibling tools, but the context of when updates are permitted is well specified.

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