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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the side effect of mark_read (flags events read and affects future calls), the shape of returned items, and the existence of an equivalent GET endpoint. It does not mention auth or rate limits, but those are less critical given the annotations. The mark_read behavior is a notable addition since it reveals a state-changing aspect.

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?

Three sentences, front-loaded with the core purpose. Each sentence adds concrete detail: what it returns, how to filter and mark read, and a note on polling with an alternative URL. There is no redundant or wasted wording, making it both concise and well-structured.

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?

Given there is no output schema, the description provides essential return-field details (source, citation_uri, raw payload) and explains the mark_read semantics. It also covers the full usage flow (filtering, polling) and gives an external access path. With all params documented in the schema and safety covered by annotations, this description is highly complete for the tool's complexity.

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 schema already describes all 5 parameters, so baseline is 3. The description adds value by giving an example type (sec_8k), explicitly showing that type and since can be combined, and clarifying the consequence of mark_read (next call only shows newer). These details go beyond the basic property descriptions.

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 'Pull fired events from your subscription feed', which clearly names a specific verb and resource. It distinguishes itself from siblings like recent_changes by emphasizing the evaluator-written persisted feed and the return payload contents. This makes the tool's unique purpose immediately clear.

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 explains usage context: how to filter by type and since, the mark_read option for incremental reads, and states that polling is fine. It also offers an alternative HTTP endpoint for scripts/dashboards, which is a helpful alternative. However, it does not explicitly compare to sibling MCP tools or state when not to use it, 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.