subscription_updates

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

Goes well beyond the readOnlyHint annotation: it discloses ordering, the still-open-only filter, that matching runs every few minutes, that an alert only matches postings created after it and therefore starts empty, and the meaning of the `delivered` field. These are exactly the non-obvious behaviors an agent could otherwise misreport to a user.

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 core definition, then filtering, then the timing caveat, in three dense sentences with no filler. The 'matching runs every few minutes' clause earns its place by preventing a wrong interpretation of an empty result.

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?

With no output schema, the description usefully explains the `delivered` field and the empty-until-matched behavior, which are the key unknowns. It stops short of describing the rest of the response shape or how `limit` interacts with paging, leaving a small gap for a four-parameter list tool.

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% and documents id, days (default 7, max 30), limit, and since with RFC 3339 format. The description largely restates id/window semantics already present in the schema, and omits `limit` entirely; it adds little semantic depth beyond what the structured fields provide, so the baseline of 3 applies.

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 — listing postings matched by the person's job alerts — and immediately scopes it with 'the same matches their alerts are built from', which separates it from generic search or the alert-listing siblings. The ordering ('newest first') and filter ('still-open postings only') further pin down exactly what set is returned.

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?

Clear context for when this is the right tool (seeing what alerts surfaced) and how to narrow with id/since/days. It does not explicitly name alternatives such as `search` for general browsing or `list_subscriptions` for the alert definitions themselves, so the agent must infer the boundary from wording rather than an explicit 'use X instead'.

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