Scan, read or clear stored project patterns

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

Annotations already flag destructiveHint=true and non-readOnly, and the description is consistent, clarifying that 'clear' is what deletes the stored patterns. It adds a prerequisite the schema cannot express: storing requires DELIVERY_PATTERN_MEMORY_ENABLED=true in the server environment, which is high-value operational context. What's missing is where patterns live (per-repo vs global) or whether a scan overwrites existing entries.

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?

Three tight sentences, front-loaded with the core capability, then the action breakdown, then the environment prerequisite. No filler or repetition.

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 an output schema present, return values need no explanation, and the env-var prerequisite plus action semantics cover the main gaps. For a tool that mutates stored state, a note on persistence scope and overwrite behavior would complete 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?

Schema coverage is 50%, with repoPath documented as 'Repository to inspect'. The description compensates for the bare enum by defining what each action does, which the enum values alone do not convey. It does not note repoPath's default of '.' or that it is ignored for get/clear.

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 and resource: 'Detect the repository's conventions (framework, test layout, tooling) and store them', plus the subordinate read/delete actions. It is distinguishable from siblings like delivery_generate or delivery_check_changes, though it never explicitly names when to prefer this over them.

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 maps each of the three actions to a concrete effect ('scan = detect and store, get = read stored patterns, clear = delete them'), which is genuine when-to-use guidance for the enum. It stops short of saying when a whole scan is warranted versus falling back to another delivery tool.

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