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

Annotations already cover readOnly, idempotent, openWorld, and non-destructive traits. The description adds meaningful context beyond those: events are written by 'the evaluator' to a persisted feed, each event includes specific fields, mark_read:true has a side effect (flagging read so next call shows newer ones), and the same feed is available externally. This transparently discloses the state-changing behavior of mark_read, which is not fully implied by the annotations alone.

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 tightly-packed sentences with zero fluff. The first sentence states the core action, the second describes the return structure, the third explains filtering and mark_read side effect, and the fourth offers an alternative access path. Every sentence earns its place, and the most critical information is front-loaded.

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?

Despite having no output schema, the description explains what is returned (source, citation_uri, raw payload) and the filtering/marking behavior. It covers the tool's purpose, parameters, side effects, and alternative access. Given the tool's moderate complexity and the rich schema/anatations, this description is fully complete for an AI agent to select and invoke it correctly.

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 input schema has 100% coverage for all 5 parameters, so the baseline is 3. The description adds extra value by giving a concrete type example ('sec_8k'), explaining the since parameter as ISO timestamp, and elaborating on mark_read's effect ('so the next call only shows newer ones') which goes beyond the schema's single-line description. It does not repeat limit/unread_only details, but those are already well-documented in 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?

The description opens with a specific verb+resource construction ('Pull fired events from your subscription feed') that immediately distinguishes it from sibling tools like list_subscriptions. It clearly identifies the return payload (source, citation_uri, raw event payload) and the filtering options, making the tool's purpose unambiguous.

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?

Provides clear usage context: polling is endorsed, filtering by type and since is described, mark_read behavior is explained, and an alternative access method (GET registry.pipeworx.io/alerts.json) is given. It does not explicitly name exclusions or compare against sibling tools, but the guidance is sufficient for correct selection and invocation.

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