recall_context

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

Beyond the readOnlyHint annotation, the description discloses matching semantics (query terms matched verbatim against transcript text), output specificity (one digest, not many), and the expected user-facing deja-vu line. It also instructs not to mention recalls that did not help, adding useful behavioral context.

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 front-loaded with the core purpose and remains dense without fluff. Some longer usage instructions about when to mention the recall could be trimmed, but each sentence contributes meaningful guidance for tool selection and invocation.

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?

Given no output schema and no title, the description fully compensates by specifying output size and content (markdown digest, problem/decisions/outcome), matching behavior, when to use it, and the interaction protocol for surfacing results to the user. The tool is complex enough that this level of detail is necessary and sufficient.

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 100% and both parameters are documented, so the baseline is 3. The description adds valuable guidance on how to construct the query parameter—using verbatim tokens like error strings, function names, or flags—which goes beyond the schema's generic 'Search terms identifying the session to digest.'

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 clearly states the tool returns a full markdown digest of the single best-matching prior session, covering problem, decisions, and outcome. It distinguishes itself from the sibling recall tool by emphasizing one deep digest versus browsing many sessions.

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 explicitly says to use it after recall, or directly when the user asks to be reminded how something was handled. It also gives an exclusion criterion: 'Not for browsing many sessions — use recall for that,' naming the alternative sibling tool directly.

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