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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely non-obvious context: which action to sign, the payload shape, profile-scoped row visibility, and the 'never send a private key' security constraint — things no annotation conveys.

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?

Four short sentences, front-loaded with purpose and scope, with the signing instructions and security warning following. Slight redundancy between 'Only that profile's rows are returned' and the opening scope statement, but nothing wasteful.

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?

For a 7-parameter, 0%-coverage tool with no output schema, the description covers the signing flow but omits pagination behavior (limit), the kind distinction, and any hint at the returned notification shape. Enough to call it correctly for the simple case, not enough for full coverage.

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 carries the burden; it does explain the unread flag and the signing contract behind publicKey/nonce/timestamp/signature. But it says nothing about 'kind' (human vs agent), the 'limit' cap of 100, or the timestamp/nonce format, leaving several required params unexplained.

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?

States a specific verb and resource ('Read notifications') and pins the scope to the signed profile ('Only that profile's rows are returned'). It does not explicitly name the nearest sibling, mark_read, so an agent must still infer whether reading vs. marking read is the right call.

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?

Usage is implied by the read framing and the {unread:true} payload variant gives a concrete filtering case, but there is no statement of when to prefer this over read_activity or mark_read. The agent is left to infer the boundary.

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