summarize_recent

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

With no annotations, the description carries the full burden and does well: it discloses a write side effect (results stored in the message_summaries table), idempotency with a 5-minute cache tolerance, LLM usage, and thread grouping. It omits permissions/auth requirements and LLM cost implications, but the behavioral disclosure is well above average.

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?

Front-loads the core purpose in the first sentence, then layers storage/idempotency and parameters in a scannable numpy-style layout. Some default values are repeated from the schema, but given 0% schema coverage the parameter block earns its space.

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?

An output schema exists, so return values need no explanation, and the description covers storage location, idempotency, and every parameter. For a 6-param, no-annotation tool it is nearly complete, missing only permission/authorization context for what is effectively a mutating, LLM-costing operation.

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 and largely does: it documents all six parameters with types, defaults, and meaning (llm_mode 'refine the summary', max_messages 'capped at 500', format 'json or toon'). Gaps remain — llm_model lists no valid values and project_key's format is only loosely described — so it stops short of fully compensating.

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?

States a specific verb (summarize) plus resource (recent project messages) and scope (time window), and implicitly distinguishes itself from summarize_thread by producing a 'project-wide summary' rather than a thread-level one. An agent can identify the operation without opening the schema.

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?

Clear context: fetch messages over a window, group by thread, and store for retrieval via fetch_summary — so it routes the agent to the sibling for reading results. However, it never explicitly states when to prefer this over summarize_thread or search_messages, leaving that comparison to inference.

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