tool_list

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: it is read-only, never raises on a query matching nothing, is always registered even when DOCKER_MCP_SERVER_DISABLE drops every domain, and explains that dropped tools are absent rather than flagged, with hidden_by_configuration reporting counts. It also discloses the return shape. The only minor gap is that it doesn't explicitly state rate limits or auth requirements, but those are not relevant for a local read-only listing tool. This is strong behavioral disclosure.

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?

The description is dense but well-organized: it opens with the core purpose, then explains the tool's unique value, then gives usage scenarios, then parameter semantics, then return format. Every sentence earns its place, and the most important information (what it lists and how it filters) is front-loaded. It is longer than a typical description, but the length is justified by the tool's role as a cross-cutting query surface. A small deduction for the return-format section being somewhat verbose, but it is still efficient.

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 read-only listing tool with no output schema, the description is complete: it explains what the tool returns (matched count, tools array with fields, domains map, no_domain count, hidden_by_configuration, switches, filters), how to use each parameter, when to use it vs alternatives, and its behavioral guarantees. An agent has everything needed to call it correctly and interpret the result. The absence of an output schema is fully compensated by the detailed return description.

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 carries the full burden of explaining parameters. It does this well: domain is 'exact domain name (see any result's domains key); omit for every domain', category is 'exact category; omit for all three', and keyword is 'case-insensitive substring over tool names, summaries and parameter names'. It also explains the enum values for category implicitly by referencing the three categories. The only slight gap is that it doesn't enumerate the exact category enum values in the description, but the schema already provides them, and the description adds the semantics of omission. This is strong compensation for the 0% schema coverage.

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 states a specific verb ('List') and resource ('this server's registered tools'), and immediately distinguishes itself from sibling tools like docs_lookup and from per-tool definitions. It also explains what makes it unique: it is the only way to ask cross-cutting questions like which tools are destructive or accept a host. This is a clear, specific purpose that an agent can act on.

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 gives explicit when-to-use guidance: use it to brief on an unfamiliar area, check blast radius, or establish a definitive negative (matched: 0). It also names the alternative (docs_lookup) and explains the boundary: this tool covers the server's own surface, while docs_lookup covers external Docker reference documentation. It even notes when not to use it: rows are summaries, so fetch a tool's own definition for parameters. This is exemplary usage guidance.

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