pubsub_peek

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

With no annotations, the description carries the full burden and does so well on the critical trait: no pulling, leasing or acking, so message state is not mutated. It also names the returned per-message fields, giving the agent a substitute for a missing output schema. It omits permission requirements and any note on cost or rate limits for large backlogs.

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?

One sentence, front-loaded with the verb and resource, and the non-destructive qualifier arrives before the payload list. Nothing redundant.

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 5-parameter read tool with no annotations and no output schema, the definition covers the essentials: it says the operation is non-mutating and enumerates what is returned for each message. Pagination is only implied via the cursor parameter in the schema, and permissions/limits are unaddressed, keeping it below 5.

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 full/limit/state/cursor/subscription are all already documented with their defaults and bounds. The description reinforces that per-message state, attempts, attributes and data are surfaced, but adds no new syntax or format meaning beyond the schema.

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 ('peek') and resource ('subscription's backlog'), plus the scope constraint 'in delivery order'. It distinguishes itself from the write-side siblings (pubsub_publish) and from a consuming subscriber by explicitly saying it does not pull, lease or ack.

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 makes clear this is the inspection path rather than a consumption path, which implicitly tells an agent to use it for read-only backlog diagnostics instead of a pull/ack flow. It does not name a specific sibling alternative or state exclusions such as 'not for draining a subscription' explicitly, so it falls short of a 5.

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