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

Adds useful context beyond the readOnlyHint annotation: 'No auth required' and the fact that the response is a compact one-line-per-service format with specific field keys. What it doesn't cover is volume/pagination behavior or whether the listing is filtered by tenant or permissions — minor gaps for a zero-param discovery tool.

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 short clauses with the tier, the output shape, the entry-point instruction, and the next step, all front-loaded. Every sentence carries information an agent would otherwise have to infer.

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 compensates by sketching the return format and field abbreviations, and it supplies the auth and sequencing facts an agent needs. Nothing essential for calling this tool correctly is missing.

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?

The tool takes zero parameters, so the baseline is 4; the description correctly implies no input is needed by not asking for any. No additional parameter guidance is possible or required here.

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 ('the service directory') and describes the exact shape of what is returned ('one token-dense line per service: s:name st:status cost:class ops:N — purpose'). It clearly distinguishes itself from the sibling simpler.describe_service by positioning itself as the listing step rather than the detail step.

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 says 'START HERE instead of reading every tool', which is a direct when/when-not instruction against the alternative of enumerating tools. It also names the follow-up tool and the required argument ('with a service name from the listing'), leaving no ambiguity about the sequence.

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