functions_invoke

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

With no annotations at all, the description carries the full behavioral burden. It does add real context: the payload is shaped as the official functions shell sends it, and the event body varies by trigger type (Firestore before/after, Storage, Pub/Sub, Auth, schedule, Eventarc, task queue). It omits the operationally important parts — that this executes arbitrary user code with real side effects, whether the call blocks until the function returns, timeout/error behavior, and what a failed invocation looks like.

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?

A single dense sentence, front-loaded with the verb and the two-mode split, with no filler. The long parenthetical event-source list is informative but makes the sentence heavy; a short second sentence enumerating the modes would read better.

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?

For a 9-parameter tool that executes code and has no output schema, the description is adequate but incomplete: it never says what comes back (the function's return value? a status? an error envelope?), which is the key unknown when no output schema exists. The unused-in-description parameters (`auth`, `params`, `method`, `region`, `resource`, `eventType`) are covered by the schema, so the gap is mainly around results and failure modes.

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 baseline would be 3. The description earns the bump by explaining the cross-parameter relationship the schema cannot: `data` pairs with the callable path (sent as {"data": ...}) while `eventData` selects the background path and determines the payload shape, with `eventType` as the Eventarc override. This maps parameters to modes rather than merely restating them.

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?

Names a specific verb ("Invoke") and resource ("a loaded function"), and immediately splits the operation into its two real modes: an HTTPS/callable request driven by `data`, or a background event driven by `eventData`. It stops short of distinguishing itself from nearby siblings such as `functions_replay_call`, `functions_list_calls`, or `eventarc_publish`, which an agent could plausibly confuse it with.

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 implies the usage condition — the function must already be loaded/emulated — and the data-vs-eventData split implicitly tells you which mode to pick. But there is no explicit when-to-use versus alternatives, no statement of prerequisites (does the emulator need to be running? does the function need to be deployed?), and no guidance on when to prefer `functions_replay_call` or `eventarc_publish` instead.

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