jb_get_results

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

No annotations are provided, so the description carries the full burden. It discloses the free/costless nature, the exact return data, the significance of verdictFound=false ('not a negative'), and the error condition for unexecuted searches. It also notes that matchRate is 'banded' and that criteria-met count doesn't discriminate at the top of a ranked list. This is rich behavioral detail well beyond structured fields, giving the agent a clear understanding of what happens when calling the tool.

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 description is long but every sentence earns its place: the first line states the action and output, the cost note is critical, the 'READING THE RESULTS' section is indispensable for correct interpretation, and the final error note is essential. It's well-structured with clear sections (purpose, cost, interpretation, error condition). No fluff 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?

There is no output schema, but the description enumerates the return fields and explains the semantic meaning of matchRate and verdicts (including the crucial 'unknown ≠ negative' nuance). It covers error behavior, limits, and the relationship to search execution. With four parameters fully documented in the schema and the description adding inter-tool references, an agent has everything necessary to correctly invoke and interpret results.

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?

The input schema covers all parameters with descriptions at 100% coverage, so the baseline is 3. The description adds meaningful context: it tells the agent that searchId comes from jb_list_searches, that projectId is a specific format and can be omitted to use a default project, and that limit has a default of 50 and max of 500. These references connect the tool to its ecosystem and clarify usage, exceeding the schema's raw field meanings.

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 begins with a specific verb ('Pull') and a specific resource ('a saved search's ranked candidates'), and details the exact fields returned (name, LinkedIn URL, title, company, location, matchRate, per-criterion verdicts). This clearly distinguishes it from siblings like jb_list_searches (which lists searches) and jb_count (counts). The scope is precise and non-tautological.

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?

The description explicitly states that this costs no export credits and is the same surface as the results page, giving context on when it's appropriate. It also provides a prerequisite: 'If the search has never been executed, this errors — open it in the app and press Run search once.' It doesn't explicitly name sibling alternatives, but the distinct purposes of siblings (list, count, run) make the usage boundary clear. The 'READING THE RESULTS' section adds interpretive guidance, though it's more about reading the output than choosing when to use the tool.

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