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

Beyond the readOnlyHint annotation, the description adds crucial behavioral context: it returns only key names with expiry and last-update time, filters expired keys, has no pagination, and applies the limit before expiry filtering, which can result in short pages. This rich detail prevents surprises and is consistent with 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?

Five sentences, each serving a purpose: stating the action, the use case, the return content, the limitation on walking large namespaces, and the ordering nuance with the limit. It is front-loaded with the core purpose and free of fluff.

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?

Despite having no output schema, the description fully describes what the return value includes (key names, expiry, last-update time, never values) and covers edge cases like expired keys and short pages. It is appropriately complete for a list tool with minimal parameters and clear sibling differentiation.

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 covers all three parameters, so baseline is 3. The description adds extra semantics for 'prefix' (narrowing results) and 'limit' (interaction with expiry filtering causing short pages), going beyond the raw schema definitions. Useful context is provided without redundancy.

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 'List the keys held in your namespace, optionally narrowed to those starting with a prefix,' providing a specific verb and resource. It explicitly contrasts with kv_get by stating it returns key names and metadata, never values, which distinguishes it from the sibling tool.

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 explicitly says to use this tool 'to discover what earlier runs saved before deciding what to fetch with kv_get,' giving a clear use case and naming the alternative. It also conveys usage limitations (no cursor/offset, need to narrow prefix for large namespaces) that guide when and how to use it.

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