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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral facts — the 90-day lookback cap, newest-pickup-first ordering, and the full-page-means-more-pages inference rule. It doesn't state rate limits or whether a total count is returned, but the read-only safety profile is already covered by annotations.

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?

Three tight sentences, front-loaded with scope and ordering, then filters, then pagination. The trailing 'Stuart: GET /v2/jobs' endpoint mapping adds little for an agent that never constructs URLs, but everything else earns its place.

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 five optional params, no output schema, and read-only annotations, the description covers the remaining gaps itself: timeframe, sort order, return contents (tracking URLs, courier proof, driver, pricing) and how to page through results. Nothing needed to call it correctly is missing.

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%, so the baseline is 3. The description goes beyond it by explaining the pagination contract between page and per_page, which the schema only lists as integers, and by framing active/status/client_reference as the intended filtering axes.

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 ('List the delivery jobs') plus the exact scope (last 90 days, newest pickup first) and what each row carries. The list-vs-single distinction is clear against stuart_get_job, and no agent could confuse it with stuart_create_job or stuart_cancel_job.

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?

Gives concrete selection guidance: filter by status, active, or client_reference, and the pagination rule ('when a page returns per_page rows, ask for the next page'). It never explicitly says when to prefer stuart_get_job for a single job, so it stops short of full alternative routing.

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