list_presets

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

With no annotations present, the description carries the full burden and does useful work: 'Read-only; never returns secret values' pre-answers the two things an agent most needs to know about a credential-adjacent listing tool. It also discloses the exact return shape including enum values (http|ssh, auto|prompt|deny). It stops short of stating auth requirements, ordering, or pagination behavior for large preset sets.

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 verb and resource in the first clause, then the return fields, then the safety note, then routing. Four tight clauses with no filler. The final sentence about get_secret_for_env earns its place as routing guidance but is the weakest link — it is about a sibling's usage more than this tool's.

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?

A zero-parameter, read-only discovery tool with an output schema and no annotations: everything an agent needs is present. Purpose, return fields, safety profile, and sibling routing are all covered, and the output schema handles the return structure so no further detail is owed.

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?

Zero parameters, so there is no semantic gap for the description to fill and the baseline of 4 applies. The description correctly spends no words on arguments and instead explains the return shape, which is the only remaining surface for a parameterless tool.

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 ('List available mcp-warden presets') and goes further by defining what a preset is: 'named, scoped actions you may invoke.' That definition plus the enumerated return fields (name, description, type, approval policy) makes it unmistakably distinct from the execution siblings like proxy_http and ssh_exec.

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 routes the agent away from this tool when action is needed: 'Use `proxy_http` for HTTP actions and `get_secret_for_env` only as a last resort.' That is explicit guidance on alternatives. What it never states outright is the inverse trigger — 'call this first to discover which preset to invoke' — so the when-to-use side is inferred from the word 'List' rather than declared.

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