project_info

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

With no annotations, the description carries the full burden. It does disclose observable behaviors like list truncation ('long lists cut to 25 + count') and format trade-offs ('yaml default, token-cheap'), which adds value. However, it does not mention side-effect safety (e.g., read-only nature), failure modes, or prerequisites like an active project, leaving some behavioral aspects undisclosed.

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?

Three sentences with no filler. The purpose is front-loaded, followed by concise parameter documentation. Each clause earns its place, and the format is scannable and directly useful.

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 simple getter with no required parameters and no output schema, the description adequately covers the tool's data scope and output options. It lacks explicit return-structure details for the different detail levels and any error-handling notes, but the simple nature of the tool means these are minor gaps.

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 0%, so the description must fully compensate. It does: each parameter is explained with its allowed values and their concrete effects (full/summary/minimal for detail; yaml/json and token-cheap for response_format). This goes well beyond the bare schema and gives the agent actionable semantic understanding.

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-like action: retrieving 'Project + app metadata' and enumerates the fields (name, folder, version, cook rate). It is clear what the tool does, but it does not explicitly differentiate itself from siblings like system_info or project_snapshot, so it misses the top score for sibling distinction.

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?

There is no guidance on when to use this tool versus alternatives such as project_snapshot, project_versions, or system_info. The description only explains parameter options, not selection criteria or exclusions. The agent is left to infer the appropriate context from the tool name and metadata scope.

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