mark_as_unread

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

Annotations already cover readOnly=false, destructive=false, idempotent=true, openWorld=false, but the description adds what those flags cannot: that the change is local-only, that already-sent read receipts and other devices are unaffected, that unknown ids are silently ignored, and the exact return shape {status, count}. The 'unknown ids are ignored' behavior is especially valuable side-effect disclosure.

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?

Front-loads the action and the store scope, then layers consequence, scope caveat, parameter semantics and return shape in short clauses. Every sentence carries distinct information; nothing repeats the schema or annotations without adding meaning.

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?

There is no output schema, yet the description supplies the return contract ({status, count} where count is the number of ids passed), the idempotency guarantee, and the blast radius of the mutation. For a single-parameter local mutation tool, an agent has everything needed to call it correctly.

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% so the baseline is 3, but the description earns an extra point by telling the agent where valid ids come from ('exactly as returned by get_conversation, get_unread or search_messages') and what happens to ids that don't resolve. It doesn't add ordering or size-limit constraints, so it isn't a full 5.

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?

Names a specific verb (mark as unread) plus resource (messages) and scopes it precisely to the local signal-mcp store, then states the observable consequence ('so get_unread returns them on its next call'). It also distinguishes itself from the sibling it most resembles, send_read_receipt, calling it 'the opposite, outward action'.

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?

Gives a concrete motivating scenario ('e.g. to flag for follow-up') and points at the contrasting sibling (send_read_receipt) for the outward case. It stops short of explicit when-not conditions or edge-case routing, but the context is clear enough to choose between the two.

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