codelattice_project

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

Annotations already disclose read-only and idempotent behavior, so the description need not repeat that. It adds mode-specific behavioral context — e.g., 'job modes for large repos' implies non-blocking behavior, and 'static risk orientation' clarifies the tool does not execute code. Minor gap: no mention of output shape or pagination, but that is partially covered by the detail parameter in the schema.

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?

Four sentences that front-load the core purpose and scope, then pack mode selection and sibling routing into two short follow-ups. No filler or repetition of schema contents. Every sentence earns its place.

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 13-parameter tool with no output schema, the description provides essential orientation: it explains the central mode parameter, gives a decision tree for repo types, and points to sibling tools for the wrong context. Parameter-specific details (page, jobId, symptom, errorText) are left to the schema, which covers them adequately. It's complete enough for an agent to pick the right mode and root, though it doesn't describe response formats.

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 high (85%), so the baseline is 3. The description adds real meaning to the mode parameter by mapping each enum value to its intended use ('quick first, standard for module/risk review, deep for detailed static evidence, diagnose for issue localization, job modes for large repos'). This goes beyond the schema's terse enum names and compensates for the few uncovered parameters.

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?

Opening phrase 'Project-level analysis for a SINGLE project root' immediately names the resource and scope. It lists concrete outputs (structure, entry points, components, static risk orientation) and explicitly differentiates from codelattice_workspace for monorepo roots. This lets an agent distinguish it from siblings without opening schemas.

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?

Provides explicit mode-to-use-case mapping: quick first, standard for module/risk review, deep for static evidence, diagnose for issue localization, job for large repos. It also states when NOT to use this tool ('For monorepo/workspace roots, use codelattice_workspace or workflow explore first') and how to proceed after. This is exactly the when/when-not guidance the dimension asks for.

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