notifications

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

With no annotations, the description carries the full burden and delivers real behavioral context: newest-first ordering, masking of security codes, the all=true scope expansion, and the Android quirk that removed notifications retain only the app name. It does not state auth or rate-limit behavior, but it discloses more than the structured fields do.

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-loaded with what the tool returns, followed by ordering, masking and the parameter hint in three tight sentences. The final sentence on Android's retention behavior is slightly tangential but earns its place as a non-obvious constraint.

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 two-parameter read tool with no output schema and no annotations, the description covers the returned content, ordering, redaction, scope expansion and a platform caveat. The unexplained limit parameter is the one notable gap, but the rest is sufficient for correct invocation.

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 all=true clearly (include permanent notifications), but says nothing about limit — its meaning, bounds or pagination behavior — leaving half the parameters undocumented in both schema and 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 names the concrete resource and what it returns (notifications on the phone, with app, time, title and text fields) plus ordering (most recent first). It is specific enough to invoke, but it never distinguishes itself from siblings like messages or look, which an agent may confuse with notification retrieval.

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 only implied through the scope hint that all=true also returns permanent/ongoing-service notifications. There is no explicit statement of when to prefer this tool over messages or look, and no prerequisites or exclusions are given.

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