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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds the one thing annotations cannot express — that the data comes from a saved store rather than live capture — which is useful context about possible staleness, but it stops there without describing liveness, refresh cadence or result size.

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?

Two tight sentences: the first front-loads what is returned and its dimensions, the second carries the access/data-source qualifier. No filler or restatement of the name, and every clause adds information.

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 one-parameter read tool with no output schema, the description covers the result shape (who/what/when) and the data source, which is enough to call it correctly. The only real gap is the undefined horizon behind 'recent' and whether results are bounded or paginated.

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?

There is a single optional parameter, and the schema documents it at 100% coverage, including the fallback behavior when it is omitted. The description adds no parameter guidance of its own, so the baseline of 3 for schema-covered parameters is the right level.

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 and resource ('Get recent changes in competitor ads') and further pins down the payload as who changed what across volume, angle and format, plus timing. The competitor-ads domain is unique among the listed siblings, so no explicit sibling callout is needed to disambiguate.

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?

'Read only, saved data' implicitly contrasts this with a live/streaming sibling, suggesting it is the lookup against stored snapshots rather than a real-time feed. However, it never states when to prefer this tool, what time window 'recent' covers, or names an alternative, so usage remains inferred rather than explicit.

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