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

Annotations already cover readOnly/destructive hints, so the description adds significant context about the persisted feed, the mark_read flag's effect on subsequent calls, and the availability of a public JSON endpoint. The optional state mutation via mark_read is clearly disclosed and does not contradict the annotations.

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?

The description is compact and information-dense, with each sentence covering a distinct aspect: core purpose, return contents, filtering, mark_read semantics, and alternative endpoint. It is front-loaded with the primary action and contains no filler.

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 all 5 parameters optional and no output schema, the description thoroughly covers the tool's behavior, including return contents, filtering, stateful mark_read, and the alternative HTTP endpoint. The unmentioned parameters (limit, unread_only) are fully documented in the schema, so nothing critical is missing.

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%, providing a baseline of 3. The description adds meaningful value by giving a concrete type example ('sec_8k') and explaining mark_read's behavioral impact beyond the schema's simple 'flag returned events read'.

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,' clearly stating the action and resource. It further details the return payload (source, citation_uri, raw event payload) and filtering capabilities, distinguishing it from sibling tools like list_subscriptions.

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 provides usage context by noting 'Polls work fine' and offering an alternative HTTP endpoint for scripts/dashboards, guiding when to use this tool versus direct API access. It also explains the effect of mark_read and filters, but does not explicitly compare against sibling MCP tools.

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