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

Beyond the readOnly/idempotent/openWorld annotations, it discloses three behaviors an agent could not infer: results are bounded, rejected CVEs are included, and the snapshot is explicitly not a complete mirror or event history. That last caveat is exactly the kind of expectation-setting that prevents misuse. It withholds the freshness window (what 'recently updated' actually spans) and any rate-limit guidance, keeping it off a 5.

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?

Four tight sentences, front-loaded with the default no-parameter behavior before introducing the incremental mode. Every sentence carries an operational fact, including the closing caveat, and there is no restatement of the title or name.

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 an output schema present, the description only needed to cover mode selection, pagination discipline, and scope caveats, all of which it does. The remaining gap is the unspecified recency window and whether the bounded snapshot has a documented size, which matters for an agent reasoning about completeness of results.

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?

The description adds real meaning beyond the 67% schema coverage: it explains that after is a checkpoint from a *completed* call and cursor is a nextCursor from an *unfinished* page, and that they are mutually exclusive modes. It also clarifies that the checkpoint is only valid to save after pagination finishes, which the schema does not state. The undescribed limit parameter is a minor, defaults-visible omission.

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 names a specific verb and resource ('get a bounded snapshot of recently updated CVEs') and separately defines the incremental mode, so the tool's identity as a change-feed reader is unmistakable. It does not explicitly contrast itself with siblings like get_cve or list_ecosystems, but the polling-feed framing is distinctive enough that confusion is unlikely.

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?

Mode selection is spelled out conditionally: omit after/cursor for a snapshot, supply after for incremental changes since a saved checkpoint. It also instructs 'Follow nextCursor and save checkpoint only after pagination completes', which is actionable sequencing guidance. The gap is that it never names an alternative tool or says when a caller should prefer this feed over fetching individual CVEs.

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