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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real context beyond them: newest-first ordering, the fact that the feed is retained regardless of tier/group preferences, and that security/billing notices always remain eligible. The required read:accounts scope is an auth detail structured fields don't carry.

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?

Purpose is front-loaded in the first clause, followed by retention/preference behavior, then auth and params. Every sentence carries information, though "Free; changes nothing" mildly duplicates readOnlyHint.

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-optional-param read tool with no output schema, the description covers ordering, retention semantics, scope requirement, and both parameters. Return shape is only partly implied ("feed, newest first"), which is the only meaningful gap.

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 description coverage is 0%, so the description must carry the load; it notes both parameters exist and are optional, and repeats the 1-50 range already encoded in the schema. It adds no meaning for unreadOnly beyond its self-explanatory name.

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+resource: "Read your in-app notification feed (newest first)", which is precise and distinguishes it from the preferences and mark-read siblings by scoping it to in-app only. It stops short of naming those siblings explicitly, which keeps it from a 5.

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?

"Needs read:accounts" and "Free; changes nothing" give the agent clear preconditions and safety context for choosing this over mutating siblings. It doesn't name alternatives or say when not to use it, so no exclusions are stated.

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