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

Annotations declare readOnlyHint=true, consistent with the tool. The description adds useful context: it takes no parameter overrides, and paid tier required with a specific error envelope for anonymous callers. It doesn't fully detail if the project state changes, but readOnlyHint covers that.

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 clear, front-loaded sentences. First sentence states purpose, second clarifies constraints, third provides guidance and tier info. No wasted words.

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?

Covers purpose, parameters, constraints, and tier requirement. With an output schema present, the return values are handled. Could mention error cases like invalid project_id, but overall sufficient for a recompute tool.

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%, but the description explains the request parameter's purpose: filtering by measurement standards. It also clarifies that no parameter overrides are taken, which adds context beyond the 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?

The description clearly states it re-runs every enabled assembly and renders aggregated BoQs across requested measurement standards. It distinguishes itself from sibling compute_* tools by explicitly noting it takes no parameter overrides.

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 description explicitly says when to use (re-run a saved project) and when not to (to revise parameters, use save_project instead). It also mentions the paid tier restriction, which guides proper usage.

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