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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real operational context beyond them: per-run input cap of 5,000 rows, output truncated to the first 300 combined rows, left-outer join semantics ('places in only some runs are kept and say which'), and the row-filtering behavior of only_changed. It does not explain ordering of output or how run names are disambiguated, which is a minor gap.

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 action (join runs on record_key, 2-6 runs) is front-loaded, and the limits and semantics follow. It is one very long run-on sentence with a few embedded clauses, so it is dense rather than cleanly structured, but nearly every clause carries information.

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 covers what matters for a join tool: valid inputs, key column, join semantics for partial matches, compare behavior, filtering, and both input and output row limits. Missing only output row ordering and how truncated rows are signalled.

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 already 80%, and the description still adds meaning: how run columns are namespaced ('each run's columns kept separate under its name'), that compare produces numeric deltas vs. text change flags, and that places missing from some runs are retained. This goes beyond restating the schema 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?

States a specific verb (join) and resource (two to six kept runs), names the join key (record_key), and specifies the scope (2-6 runs, oldest first). No sibling tool does joins on prior runs, so an agent can identify this tool immediately.

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?

It gives concrete sourcing context ('run_ids from earlier answers, or tables such as dated tabs in Drive') and a worked example ('sites whose nearest A&E got further away since September') that implies when this tool applies. It does not name a when-not condition or an alternative sibling, but none of the siblings overlap meaningfully.

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