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

Annotations declare readOnlyHint=true, and the description aligns with that by describing a read-only analytics query. The description adds valuable behavioral context beyond the annotation: it explains that 'assistants do not run scripts, so only this part shows them', which is a subtle data-behavior detail an agent needs to interpret results correctly. It also clarifies the two data sources (Umami vs server-side), which is behavioral context not present in the schema or annotations.

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 compact and front-loaded with the most important constraint ('Only for the Awning team'). It packs a lot of information into a few sentences without redundancy. The structure is a bit run-on and could be clearer with punctuation, but every sentence earns its place and there is no filler.

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?

Given the tool's simplicity (one optional parameter, no output schema), the description covers the essential context: audience restriction, data sources, metrics, and summarization instruction. It doesn't describe the exact output format, but with no output schema and a read-only analytics tool, the description's guidance on how to interpret and summarise is sufficient for an agent to invoke it correctly. Minor gap: it doesn't explicitly state what the response looks like, but the description's focus on interpretation compensates.

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 description coverage is 0%, so the description must compensate for the single 'days' parameter. The description implies the time window ('over the last days') and the instruction to compare with the previous period, which gives the agent a sense of what 'days' controls. However, it doesn't explicitly state that 'days' is the lookback window or describe its format/range, leaving some inference required. Still, with only one parameter and a clear context, the description provides enough semantic grounding.

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 clearly states the tool is for the Awning team and explains what it reports: website performance over recent days, with two distinct data sections (people and all_visits). It names specific metrics (top pages, sources, channels, countries, devices) and distinguishes the two data sources (Umami vs server-side counting). This is a specific verb+resource with clear scope, and it differentiates itself from the sibling tools, which are mostly booking/business operations.

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 restricts usage to the Awning team ('Only for the Awning team'), which is a clear when-to-use gate. It also explains the difference between the two data sections and instructs the agent on how to summarise results ('compare with the previous period and name the share of assistants'). This is explicit guidance on how to use the tool and what to do with its output.

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