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

Annotations only say readOnlyHint=false with destructiveHint=false; the description goes much further, disclosing that a validated run summary is written server-side and that the key surfaces in automation_discovery_history's doNotPropose, suppressing future offers tenant-wide including in other MCP clients. That is exactly the non-obvious side effect an agent needs before calling.

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 correctly - the action and its gating condition come first, with provenance and downstream effect after. The final sentence is a long compound clause that packs key-derivation, server behavior, and cross-client consequence together, costing some readability.

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 one-parameter mutation with no output schema and no annotations covering effects, the description supplies the scope, the precondition, and the downstream consequence. It is slightly opaque about what 'a validated run summary' actually contains, so a caller still cannot predict what the call returns.

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 0%, so the description must carry the parameter, and it does: it explains the two valid acquisition paths (task key from the reuse-candidates skill in app chat, otherwise a short lowercase-hyphen key) and supplies a concrete example matching the schema pattern. Only the maxLength bound is left unsaid, which is a minor omission.

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 ('Record a person's Not now choice') and names exactly what is being recorded - a declined repeated task or offered automation. This separates it cleanly from siblings like automation_memory_propose and automation_discovery_history without needing their schemas.

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?

Gives an explicit precondition ('Call only after the person says Not now') and tells the caller how to derive the key differently in app chat versus elsewhere. It lacks an explicit statement of the positive alternative (e.g. use automation_memory_propose when the person accepts), so the routing is clear but not fully closed.

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