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

Annotations mark this as openWorldHint=true, destructiveHint=false and readOnlyHint=false, and the description explains the surprising part of that profile: 'Uses one read and saves the result in the user's Puley history', which clarifies why a search is not read-only and implies a cost/credit model. That is genuine added context beyond the annotations, though it stops short of stating failure modes, rate limits, or pagination behavior.

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?

The return fields and data sources are front-loaded before the parameter list, and each sentence carries information. The parameter run-on is dense and slightly telegraphic ('days: any, 1, 3, 7 or 14'), but no sentence is wasted.

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 seven parameters, no output schema, and zero schema descriptions, the description supplies the return field list, the per-country board mapping, allowed parameter values, and the side effect of history-saving. What remains thin is how location interacts with country and what the query string is matched against.

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 carries the full burden and mostly delivers: it gives allowed values for days (any, 1, 3, 7, 14), sort (relevance or date), limit range (5 to 50), the format of country (two-letter code) and the special board value 'upwork' with its distinct return fields. Only query and location are left undefined, which keeps it below a 5.

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 ('Jobs for a search and place') and enumerates the returned fields (title, company, location, pay, job type, posted date, snippet, links), which makes the output shape unambiguous. It does not explicitly differentiate itself from adjacent find_* siblings such as find_leads or search_classifieds, but the job-board framing is distinctive enough to route correctly.

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 implied through the country/board coverage map and the in-tool alternative 'board: upwork for freelance work instead', which is a useful routing rule. However there is no explicit when-to-use or when-not guidance against sibling tools, and no stated prerequisites for the country/board combination.

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