Get Project

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

Annotations already establish the safe read-only, idempotent profile, so the bar is lower. The description adds non-obvious behavior beyond them: the 300-layer truncation with a 'layers_listed: false' flag, the 200-item default page size, and the instruction to relay the update field to the user.

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?

A single dense paragraph that front-loads the primary purpose and the returned fields before dropping into filter/pagination mechanics. Every clause carries information, though the run-on structure slightly reduces scannability.

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 and 0% schema coverage, the description must explain both inputs and outputs — and it does, covering the return shape, truncation semantics, pagination defaults, and the update notice. An agent has everything needed to call and interpret it.

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 0%, so the description carries the full burden. It documents all four parameters meaningfully: name is a substring match, type filters, limit defaults to 200, and offset pages the results — compensating well for the empty schema.

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 ('List project items with each comp's layers') and enumerates the returned fields (active comp id, AE version, project path), so the agent knows exactly what comes back. It also distinguishes itself from get_comp by naming that sibling as the fallback when layer data is truncated.

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?

Gives clear conditions for filtering (by name substring or type) and pagination (limit 200 / offset), plus an explicit alternative: when the page exceeds 300 layers, use get_comp instead. No explicit 'when not to use' beyond that, but the routing condition is concrete.

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