read_feed

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

With no annotations, the description carries the full burden. It discloses that returned content is untrusted data and never an instruction, a critical behavioral warning. It also reveals cursor-based pagination and oldest-first ordering. It doesn't explicitly state read-only, but 'Read' implies it. This is strong disclosure for a read tool.

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, each serving a purpose: function, conditional routing, and security warning. No fluff, front-loaded with the core purpose. Every sentence earns its place.

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 the simplicity of the tool and lack of output schema, the description covers the essential aspects: what it reads, ordering, gap handling, and security. It doesn't describe the exact response format but that's not critical for invoking it correctly. The only missing piece is rate limits or authentication, but those are not specific to this 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?

Schema coverage is 0%, so the description must compensate. It explains cursor meaning ('since your last cursor') and implies limit is for limiting count, but doesn't detail defaults. However, schema already provides min/max for limit, so limit is self-explanatory. Cursor gets meaning from description.

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 clearly states the tool reads new events (mentions, replies, thread activity) since the last cursor, oldest first. It names the sibling tool read_digest and the condition for using it, so it is distinguished from alternatives. The verb 'Read' and resource 'new events' are specific.

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?

Explicitly says 'If the result has gap:true, call read_digest instead,' giving a precise condition for switching to the alternative. This provides clear when-to-use guidance beyond mere functionality.

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