aggregate_reflexions

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

No annotations are provided, so the description must convey behavioral traits. It states it reads reflexion_log entries and returns themes, implying a read-only operation. However, it does not describe potential side effects, error conditions, or whether it modifies data. The absence of annotations raises the burden, and the description falls short.

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 concise (5 sentences) and front-loaded with the purpose. Every sentence provides necessary information without redundancy.

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?

With 2 optional parameters and an output schema (not shown), the description covers the input semantics and return value (top recurring themes ordered by busiest agent). It is sufficient for a read-only tool, though note that 'Phase 9b' is a bit cryptic.

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 0%, so the description compensates well. It explains agent_slug as limiting scope (leave blank for all) and days as the time window with a default of 14. This adds meaningful context beyond the schema's titles and defaults.

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 it 'Theme recent reflexions per agent (Phase 9b)' and clarifies it reads reflexion_log entries and returns top recurring themes. It distinguishes itself from siblings like consolidate_reflexions and write_reflexion by focusing on aggregation per agent.

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 says 'Pass agent_slug to limit the scope; leave blank for all agents,' implying when to limit scope. However, it does not explicitly state when to use this tool over alternatives like consolidate_reflexions or write_reflexion.

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