Лента уведомлений

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld behavior, so the bar is lower. The description adds valuable context beyond annotations: reading the feed does not mark records as read, which is a critical side-effect nuance not captured by the structured flags. No rate limits or return format details are given.

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?

Two short sentences, front-loaded with scope and followed by the key behavioral caveat. Every sentence earns its place with no redundancy or filler.

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 6-parameter list tool with no output schema and low schema description coverage, the description is minimally adequate. It covers overall scope and one important behavioral trait, but leaves filtering parameters and pagination defaults unexplained. It is not misleading, but clear gaps remain.

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 only 33% (2 of 6 parameters have descriptions), so the description should compensate but does not. It generically mentions filtering and pagination, but provides no semantics for kind, level, offset, or unread beyond what the bare schema shows. This leaves key parameters under-specified.

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 says it returns personal notifications for all cases with filtering and pagination, which clearly identifies a list operation. It also distinguishes itself from notifications_read by stating that reading the feed does not mark records as read. It does not explicitly name alternative siblings, so a 4 is appropriate.

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?

There is no explicit guidance on when to use this tool versus notifications_summary, notifications_filters, or notifications_read. The only distinguishing note is behavioral (non-marking), not a usage recommendation. No exclusions or context for selection are provided.

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