Recall recent work

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

Goes well beyond readOnlyHint=true by disclosing the record's shape (one line per step, not per session, because capture is incremental), that consecutive steps often overlap especially in older records, and the interpretive stance that stored text is data while the report is the answer. This materially changes how an agent should consume and relay output.

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?

Purpose is front-loaded, but the body is a long prose block dominated by report-formatting instructions (plain language, jargon, one account vs step by step) rather than tool mechanics. Much of it earns its place, yet the density and repetition make it heavier than the 4-param read tool warrants.

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 no output schema, the description usefully explains what is returned (steps in order, one line per step; brief handled by schema). Combined with readOnlyHint it covers safety and return shape adequately, though return-volume/pagination behavior is not addressed.

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 the schema already documents count, detail, window and project, including the 'not steps' nuance. The description's closing sentence restates that limiting is optional but adds no syntax or format detail beyond the schema. 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?

States a concrete purpose with verb and resource: answer 'what was I working on lately?' from captured session records, newest first. An agent can tell what it retrieves and in what order. It stops short of naming or contrasting with siblings like librarian-search or librarian-get-note, so differentiation is only implied.

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?

Usage is implied by the question it answers ('what was I working on lately?') and it notes the optional limiters. There is no explicit when-to-use vs when-to-prefer-search guidance, and the passing reference to 'a prior-engagement note on a search result' is not framed as routing to a sibling.

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