get_growth_sources

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

The description goes well beyond the readOnlyHint annotation. It discloses the number of authenticated reads (1 or 2 with include_events), explicitly states 'no writes', and details edge cases: authentication failure stops the call, truncation flags identify cut data, and the scope of total_sources/has_more. It also explains the processing limits (500 nodes, depth 3, 400 timeseries points) and the default/max return count. This is rich behavioral context that the annotation alone does not provide.

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 dense paragraph that front-loads the core purpose and constraints before delving into details. Every sentence carries information – no filler. It could be improved with bullet points for readability, but it is appropriately sized given the number of behavioral details it conveys. It is efficient and structured logically: purpose → read count → events → limits → truncation.

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?

The tool has an output schema, so the description need not explain return values. Given that, the description is remarkably complete: it covers authentication, read counts, date range constraints, pagination/limit behavior, event behavior, truncation flags, and the scope of summary fields. It even notes that authentication failure stops the call. There is no obvious missing information an agent would need to call this correctly.

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?

With schema description coverage at 0%, the description must compensate. It explains from_date/to_date via 'ordered inclusive date range', limit via 'up to 20 top-level sources by default, at most 50', and include_events via 'two when include_events is true' and the optional events report. However, include_timeseries is not explicitly described – the mention of '400 timeseries points per metric' hints at it but does not clarify the parameter's role. The description covers most parameters but leaves include_timeseries implicit, so it only partially compensates for the missing schema descriptions.

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 opens with 'Read growth sources' – a specific verb and resource – and adds a precise scope (ordered inclusive date range, ≤366 days, ending ≤tomorrow UTC). This distinguishes it from sibling tools like get_publication_stats or get_post_analytics, which target different metrics. The purpose is unambiguous.

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?

While the description clearly states what the tool does and its constraints (date range, limits, events), it does not explicitly tell the agent when to choose this over alternatives, nor does it mention any sibling tools or exclusions. The agent must infer that growth sources are distinct from analytics or subscriber tools. There is no 'use this instead of X when...' guidance.

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