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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it specifies aggregation granularity ('day totals only'), the exact sources included, and currency details (EUR for chatgpt_ads, ad account currency for google_ads). This helps the agent understand what the returned data represents without an output schema.

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 a single, information-dense sentence that front-loads the core action and scope, then lists the sources and metrics. Every clause earns its place: the 'day totals only' qualifier prevents misinterpretation, and the source/metric enumeration is essential for an agent to know what data is available. No wasted words.

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 read-only, idempotent tool with 2 well-documented parameters and no output schema, the description is nearly complete. It tells the agent what data comes back (per source and metric, day totals) and the currency nuances. The only minor gap is that it doesn't describe the exact response shape (e.g., whether it's a flat list or nested object), but with no output schema and a clear aggregation description, this is a minor omission.

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 100%, so both parameters (days and site_id) are already documented in the schema. The description adds context about the time window ('last N days') and the site_id's origin ('as returned by list_sites' is in the schema, not the description). The description doesn't add new parameter-level meaning beyond what the schema provides, so baseline 3 is appropriate.

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 states a specific verb ('Summarize'), a clear resource ('daily metrics for a website'), and a precise scope ('over the last N days, totalled per source and metric (day totals only)'). It also enumerates the exact sources and metrics, which distinguishes it from sibling tools like get_report or get_ai_visibility without needing to open their schemas.

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 clearly implies when to use this tool: when you need daily totals per source/metric for a site over a recent window. It does not explicitly name alternatives or exclusions, but the detailed source/metric list and 'day totals only' qualifier provide enough context to differentiate it from broader reporting tools. A small gap: it doesn't explicitly say 'use get_report for non-daily or cross-site analytics,' but the context is strong.

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