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

Annotations already declare readOnlyHint=true, so the redundant 'Read-only' line adds nothing, but the description goes beyond annotations by disclosing a real behavioral edge case: an Application with no connected source-control binding returns binding.connected false with a reason. It also names concrete tunables (max_reviews_per_pull_request default 5, max_runs_per_day).

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 primary object of the read, then the diagnostic framing and edge case. Dense and mostly waste-free, though 'This is where the pull-request review budget lives' is slightly rhetorical and the 'Read-only' clause repeats the annotation.

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?

There is no output schema, so the description carries the return-value burden and does so: it enumerates the lanes, states the resolved org default and override flag, names the key budget fields, and covers the unbound-repository response. An agent has enough to call and interpret this tool without further context.

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 100% and there is only one required parameter (application_id), which the schema already documents. The description adds no parameter-level detail, so the baseline of 3 applies.

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 (Read) plus resource (Ankra AI configuration for an Application's repository) and enumerates the payload: lanes, effective settings, resolved org default, and override status. It is clearly distinguishable from the sibling write tool update_application_ai_config without opening either schema.

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?

Frames concrete use cases - 'why did Ankra AI not review this PR' and 'what would I change to make it review more' - which tells the agent when this tool is the right call. It does not explicitly name the alternative (update_application_ai_config) or state when-not-to-use it, so it stops short of a 5.

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