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

Annotations already declare readOnlyHint and destructiveHint=false, and the description reinforces that with 'Effect: none, read-only.' Beyond that it adds real behavioral context: matching runs every few minutes, a newly created alert starts empty, and 'delivered' indicates whether an alert already carried the posting. Missing only pagination/limit behavior and total-count semantics, which keeps it at 4.

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?

Five compact sentences, front-loaded with what the tool returns, then filters, then behavioral caveats. Dense but each sentence carries information; the 'Effect: none, read-only' line is slightly redundant with readOnlyHint but is short enough not to waste space.

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 does well to explain 'delivered' and to characterize the returned set (newest first, still-open only), which is what an agent needs to interpret results. It is silent on the response shape beyond that and on what limit 50 truncation implies, a small gap for a list tool with fully documented parameters.

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 100%, so all four parameters are already documented, including defaults, maxima, and the since-overrides-days rule. The description repeats the id/since/days narrowing but adds little to the schema beyond the matching-window semantics tied to id; the limit parameter is not mentioned at all in the prose, so the baseline 3 is appropriate.

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?

Opens with a specific verb and resource: 'List the new postings the person's job alerts have matched,' and adds scope ('still-open postings only, newest first'). The clause 'the same matches their alerts are built from' implicitly separates it from list_subscriptions, but no sibling is named explicitly, so it lands just short of full differentiation.

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?

It explains how to narrow results (one alert by id, a window by since or days) and the caveat that an alert only matches postings appearing after its creation, which is genuine usage context. However, it never states when to reach for this instead of search_jobs, my_jobs, or list_subscriptions, leaving alternative selection to inference.

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