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

The description discloses that mark_read:true flags events as read, affecting future calls—a side-effecting behavior. This directly contradicts the readOnlyHint=true annotation, which implies no state mutation. The idempotentHint remains compatible, but the read-only hint is undermined, making this an annotation contradiction.

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 focused sentences, each earning its place: purpose and return format, filtering and read-state behavior, and alternative HTTP access. No redundancy, front-loaded with the core action, and perfectly sized for the tool's complexity.

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?

The description covers the return payload shape, filter semantics, mark_read side effect, and alternative access method—essential for a tool with no output schema. It doesn't mention unread_only or limit defaults, but the schema already documents those, so the description is adequately complete for a read-oriented tool.

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?

With 100% schema description coverage, the schema already documents all parameters. The description adds value by giving a concrete type example, clarifying that since takes an ISO timestamp, and explaining the consequence of mark_read (next call shows only newer events). This goes beyond the schema's basic parameter 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 a specific verb-resource pair ('Pull fired events from your subscription feed') and enumerates the return payload (source, citation_uri, raw event payload), making its purpose unmistakable. It distinguishes itself from siblings like list_subscriptions (which lists subscriptions) and recent_changes by focusing on fired events from the user's subscription feed.

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 practical usage context: filtering by type with a concrete example ('sec_8k') and since as an ISO timestamp, explaining mark_read's effect for incremental reads, and noting that polling works fine while pointing to an HTTP endpoint for scripts/dashboards. It lacks explicit comparisons to sibling tools but gives clear when-to-use guidance.

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