Locate Jobs Network Job Search

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's 'only reads job listings' adds little beyond structured data. The return-volume note (5 to 10 results) and result fields are useful, but they largely duplicate the schema's limit constraint and the output schema.

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-loaded with the core action before the operational details. The 27-board enumeration is long but plausibly earns space by telling the agent which employers/boards results come from; otherwise the text is tight.

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 4-optional-parameter read tool with full schema coverage, explicit annotations, and an output schema, the description covers what is needed to invoke it. Minor gap: no guidance on result ordering or what to do when a zero-result search occurs.

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 the baseline is 3. The description mostly restates schema semantics (ZIP searches its whole state, leave out for newest/whole U.S.) without adding new guidance like format tolerances or edge-case behavior.

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 ('Search live jobs on the 27 Locate Jobs Network job boards') and scopes the network by name. It never mentions the only sibling, unemployment_answers, so the agent gets no explicit differentiation, but the purposes are far apart enough that misselection is unlikely.

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 search modes (by role/skill, by city/state/ZIP, or remote) and explicitly rules out applying, posting, and saving searches. It does not point to any alternative tool or explain when a different tool would be better, but the usage context is clear.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered structurally. The description goes beyond that by explicitly listing what the tool cannot do (cannot file a claim, check claim status, or change benefits) and by disclosing the out-of-coverage fallback behavior — useful context an agent would otherwise have to infer.

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 core purpose and invocation rule are front-loaded in the first two sentences. The 13-state enumeration is long but earns its place by telling the agent exactly when the tool will succeed versus fall back, and there is no filler or repetition.

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 an output schema present, the description is not obligated to explain return values, and it instead covers the things structured fields cannot: the supported-state boundary, the substitution of topic for question, and the negative capability envelope. Nothing an agent needs to call this 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 description coverage is 100%, and the parameter descriptions already spell out the state format, the 13 enumerated topics with definitions, and the question length limit. The description's parameter content ('a name or 2-letter code', 'picks the topic from the question when none is given') largely restates the schema, so it meets the baseline without adding much beyond it.

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?

The description opens with a specific verb+resource ('A checked answer about unemployment benefits for a U.S. state') and enumerates the exact covered states, so an agent knows precisely what domain it serves. It is clearly distinct from the sibling search_jobs, which has nothing to do with benefit policy answers.

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 gives concrete invocation guidance: supply a state plus either a topic or the person's own question, and the tool infers the topic when none is supplied. It also states the fallback path for uncovered states (returns the federal locator page rather than guessing), which is a clear usage-condition statement. It lacks an explicit comparison to search_jobs, but the domains do not overlap.

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