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

Annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) cover the safety profile, and the description adds the crucial non-obvious behavior: an override REPLACES the organisation's lane wholesale, so omitted fields fall back to the platform default rather than the organisation's setting. It also clarifies that setting override=false deletes the override and that excluded lanes are untouched.

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 purpose, then the critical replace-semantics warning, then the lane-scoping rule. It is appropriately sized for a tool this complex, though a couple of sentences restate what the nested schema already documents, adding slight redundancy.

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?

No output schema exists, and the description covers the mutation's full contract: preconditions, replacement semantics, override/deletion behavior, and default values. Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3; the description still adds value by spelling out the max_reviews_per_pull_request default (5), the 0 = no cap convention, the @mention exemption, and its restriction to the pull_request lane. Much of this overlaps the schema text, so it is a modest increment over structured data rather than a full rewrite.

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 opens with a specific verb+resource ('Change how Ankra AI runs on an Application's repository') and enumerates the concrete operations (enable/disable a lane, pick model, scope branches, ignore paths, custom instructions, budget). It distinguishes itself clearly from the read sibling get_application_ai_config and from update_ai_environment.

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 an explicit precondition ('Call get_application_ai_config first'), explains the consequence of the override semantics, and states the trigger for the delete path ('Send override false for a lane to drop the override'). Scope is also bounded: 'Only lanes named in the request are touched.'

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