Recall: Tables

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's real contribution is data semantics: every record is cited with source_id, msg_id, ts and speaker, and the output data model is explained through the `owner`/`status`/`status_basis` vocabulary. That is meaningful context beyond structured fields, though ordering, pagination behavior and result volume are not disclosed.

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 core purpose is front-loaded in the first clause, and the following sentences are dense but each carries a distinct rule about citation fields or ownership semantics. It is a heavy single block with several nested parentheticals, which costs a little readability, but nothing is filler.

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 correctly carries the return-format burden by naming the citation fields and defining owner/status/status_basis, which an agent needs to interpret results safely. It is close to complete for a read tool, with only ordering and pagination left unstated.

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 limit, project and all_projects, including the 'shared is always included' and 'Ask for it explicitly' notes. The description adds essentially nothing parameter-level, making the baseline 3 correct.

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 resource ('Markdown tables from past conversations, verbatim') and clarifies the result body is the table itself. It is distinguishable from recall_search/recall_get in kind, but it never names a sibling or contrasts scope with them, so differentiation is inferential rather than explicit.

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 resource type and reinforced by a hard rule ('Never present an assistant, agent_report or audit record as the owner's decision') plus guidance that all_projects must be asked for explicitly. However, there is no statement of when to prefer this over recall_search, recall_timeline or recall_decisions, leaving selection to inference.

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