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

The description reveals that the tool requires authentication and is a paid service, returning a TIER_INSUFFICIENT error otherwise. It mentions the default supply route (CONTRACTOR_INSTALL_PC_SUPPLY) and the ability to request deliverables like xlsx, dxf, pdf. While the annotations indicate readOnlyHint=true, the description does not contradict it and adds context about billing and output generation. It lacks explicit mention of side effects or state changes, but overall provides good behavioral insight.

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?

The description is relatively long and contains domain-specific jargon (e.g., 'bundle-with-shared-envelope pattern') that may not be helpful for an AI agent. While it is front-loaded with the critical paid-tier warning, the overall structure could be more concise by removing extraneous details. The length is justified for the complexity, but it could be trimmed.

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?

The description covers key aspects like input parameters, example call, output modes, and deliverable options. However, it lacks a formal output schema description; the agent must infer return values from the text. Given the tool's complexity (nested params, many options), the description leaves some gaps (e.g., exact structure of 'full_json' output). It is adequate but not fully complete.

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?

With only 25% schema description coverage, the description partially compensates by explaining the high-level parameter categories (orifice, flap valve, weir, penstock, scour protection) and providing example parameter values and an example call. However, it does not detail each parameter's meaning or constraints beyond a few examples, so agents must rely heavily on the schema for full parameter semantics.

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 uses a specific verb ('compute') and clearly identifies the resource ('Headwall — Attenuation Outlet BoQ'). It distinguishes from sibling tool 'compute_headwall' by noting it is the paid-tier alternative. The purpose is unambiguous: it computes a bill of quantities for a controlled attenuation outlet headwall with ironmongery and scour protection.

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 states it is paid-tier only and directs users to the free-tier alternative 'compute_headwall' for unpaid access. It provides a URL for pricing and mentions authentication requirements. It also gives example parameters and an example call, helping the agent understand when and how to use the tool.

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