metadata

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

No annotations exist, so the description carries the full behavioral burden. It implies a read-only introspection operation but never says so explicitly, nor does it discuss cost/latency on large configurations, error behavior for an invalid path, or what happens when no session is open. It does convey the response shaping (composition vs. detail) that matters most for interpreting results, which keeps it above a bare restatement.

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?

One dense but front-loaded sentence that puts the resource first and then the two operating modes. Every clause carries information; the long enumeration of detail types is the only place it could be trimmed, but that enumeration is what makes the tool's scope concrete.

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?

An output schema exists, so return-value formatting need not be explained, and all five parameters are fully described in the schema. The description fills in the conceptual model (composition vs. object detail) plus the extension-object caveat. It is nearly complete, lacking only failure modes and the read-only guarantee for a tool with no annotations.

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 100%, so the baseline is 3. The description usefully restates the path/filter interplay in the tool body and adds the list of detail categories returned under `path`, but it says nothing about `format`, `session`, or `timeout` beyond what the schema already documents explicitly.

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 resource (configuration metadata of a session, including extension objects) and enumerates the concrete artifacts returned: attributes, tabular sections, dimensions, resources, enum values, movements, forms, commands, layouts. The sibling tools (query, eval, execute, result, sessions) are clearly different in kind, so no explicit differentiation is needed, but the name 'metadata' is generic and the description itself carries the disambiguation.

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 gives clear mode-selection guidance: without `path` you get the composition by collections, with `filter` only matching objects, and with `path` you get the object's details. What is missing is any statement of when to prefer this over `query` or `eval` for schema inspection, but within the tool the branching is well signposted.

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