get_project_metadata

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

No annotations are provided, so the description carries the behavioral burden, and it does disclose 'Side effects: none,' making the read-only nature explicit. It also surfaces a non-obvious edge case (unsaved Sets have an empty file path), which is genuinely useful behavioral context, though it says nothing about error or return semantics.

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?

It is front-loaded with the payload before side effects, examples, and edge cases, and every sentence adds some value. The example line ('get_project_metadata() identifies the loaded Set') is mildly redundant with the opening sentence and could be trimmed.

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?

There is no output schema, so the description must cover returns, and it does by enumerating the three fields (name, path, dirty state) plus the unsaved-Set edge case. It would be stronger if it distinguished the returned data from the overlapping get_session_* siblings, but for a zero-param read it is otherwise complete.

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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter behavior the description could clarify. The schema's empty object is self-explanatory and the description correctly implies a callable-with-no-args operation.

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 names a specific verb ('Read') and the exact fields returned (Set name, file path, dirty state), so the resource and payload are unambiguous. It does not, however, differentiate itself from overlapping siblings like get_session_overview or get_session_info, which likely also expose project/session identity data.

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 only usage signal is the example 'get_project_metadata() identifies the loaded Set,' which implies a scenario but gives no explicit when-to-use, when-not, or alternatives. With several sibling introspection tools (get_session_info, get_session_overview, get_selected_context) available, the absence of routing guidance is a real gap.

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