inspect_project

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered; the description adds genuine extra context by naming the underlying data sources (.lcp manifest and class sources) that determine what the inventory reflects. It stops short of describing behavior on a missing/invalid lcp_path or the summary-vs-detail output tradeoff, which would have pushed it higher.

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?

Two sentences, both earning their place: the first defines scope and payload, the second routes the agent to the follow-up tool. Front-loaded with the read-only inventory statement and no filler.

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?

With no output schema, the description does outline the returned entities (classes, channels, tasks, networks, objects) and points at the manifest as the source, which is adequate for a four-parameter read tool. Minor gaps remain around failure behavior for an invalid lcp_path and the exact summary-vs-full output distinction.

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 100%, so the four parameters are already fully documented in the schema, including the drill-down semantics of class_names and the include_networks/include_connections dependency. The description only echoes the return shape ('classes (name, channels, tasks)') and adds no format or defaulting detail beyond the schema, so baseline 3 applies.

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 ('Read-only inventory of the CLASS 2 project') and enumerates exactly what is returned (classes with name/channels/tasks, networks and objects). It also names its data sources (.lcp manifest and class sources), which makes it clearly distinguishable from mutation siblings like apply_project_changes and manage_class2.

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?

Explicitly states the use case: 'Use it to plan changes before apply_project_changes,' which gives the agent a clear trigger. It does not, however, distinguish this tool from other read siblings such as read_class_source or lse_project/visu_project, so the agent gets context but no exclusions.

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