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

The description states 'Set mark_read:true to flag returned events read so the next call only shows newer ones,' which is a state-changing side effect. This directly contradicts the annotation readOnlyHint:true. The annotation claims the tool is read-only, but the description reveals a write operation, making the behavior misleading.

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 a single paragraph of about four sentences, each earning its place: it states purpose, return fields, filtering options, mark_read behavior, polling note, and alternative endpoint. No wasted words, and it leads with the core action.

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 5 parameters and no output schema, the description covers return format (source, citation_uri, payload), filtering, mark_read semantics, polling suitability, and an HTTP alternative. It does not explicitly explain unread_only or limit defaults, but these are in the schema. The contradiction with readOnlyHint slightly undermines completeness, so not a 5.

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 coverage is 100%, providing baseline 3. The description adds meaningful semantics beyond the schema by giving an example for type ('sec_8k'), clarifying the since format (ISO timestamp), and explaining the effect of mark_read (only newer events on next call). This extra context justifies a 4.

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 and resource: 'Pull fired events from your subscription feed.' It clearly explains the tool returns recent alerts with their source, citation_uri, and raw payload, distinguishing it from siblings like recent_changes or list_subscriptions by focusing on alerts and the persisted 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?

It gives a clear usage context: polling works fine, filtering by type and since, and using mark_read/unread_only. However, it does not explicitly name when to use this tool over siblings, only mentions an alternative HTTP endpoint. This is clear context without exclusions, so a 4 is appropriate.

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