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

Annotations already declare readOnly, idempotent and closed-world, so safety is covered. The description adds genuinely non-obvious behavior beyond that: fact counts and coverage dates are precomputed summary data, while the per-fact retrieval timestamp is the authoritative freshness signal — a caveat that would otherwise cause an agent to misreport freshness.

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?

Front-loaded with the payload (what fields come back) before the invocation trigger and the freshness caveat, which is the correct ordering. Dense but each sentence adds either scope, a use trigger, or a behavioral caveat; only the last sentence borders on over-explanation.

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 one optional parameter, no output schema and annotations covering the safety profile, the description supplies everything needed: both call modes, what is returned, and the precomputed-vs-authoritative freshness distinction. It does not enumerate the returned fields' types, but for a single-param read tool that gap is minor.

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 coverage is 100% and the single parameter's description already documents the id examples and the omit-to-list behavior, so the description is largely redundant here. It reinforces the id format ('dol_ndcp') but adds no syntax beyond the schema. Baseline 3 is appropriate when the schema carries the parameter meaning.

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?

Names a specific verb+resource (get_source) and precisely enumerates what it returns: publisher, licence, access method, fact count, covered period, citation. It also states the dual mode — one source when given an id, the full list when called without arguments — so an agent can distinguish it from get_facts or search_facts immediately.

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 explicit triggering conditions: 'use it whenever you are asked where a number comes from, whether it may be reused, or how current it is.' That covers provenance, licensing and freshness questions well. It stops short of naming an alternative sibling (e.g. when to prefer search_facts), so it is clear context without explicit exclusions.

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