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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial non-obvious behavior: figures are per-publisher counts with inconsistent methodology, cross-company aggregation/ranking is invalid, missing means not reported rather than zero, national-security values stay banded, and the counts cannot reveal individual data requests. This is exactly the kind of interpretive constraint an agent cannot get from structured fields.

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 what it returns, then the caveats, then defaults — a sound ordering for a caveat-heavy tool. Some phrasing is duplicated in the parameter schema (national-security bands, 'not reported, not zero'), which costs a little density but reinforces the highest-risk misinterpretations.

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?

For a 7-parameter read tool with full schema coverage and annotations, the description supplies the interpretive guardrails that matter most. It does not describe the shape of returned facts (no output schema exists), so an agent knows the rules but not the payload structure — a modest remaining gap.

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%, so the baseline is 3, but the description adds meaning beyond the schema by explaining that filters select exact fact fields and that period falls back to the latest complete report. The units/methodology caveat also contextualizes what 'measure' and 'series' identifiers imply.

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 names a specific verb and resource: 'Returns one publisher's figures for one report in the MORVS Government Data Demand Register.' The 'one publisher' scoping implicitly separates it from data_demand_compare, but no sibling is named outright. Purpose is clear without opening the schema.

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?

It states the default behavior ('Defaults to the latest complete report') and that optional filters narrow to exact fact fields, which is useful context for invocation. However, it never says when to pick this over data_demand_compare or data_broker_check — the alternative routing is left to inference from the 'one publisher' phrasing.

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