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

Annotations only cover read-only and idempotent safety; the description goes well beyond them by disclosing the 20-item page cap, ranking order, the exact pagination loop with next_cursor, and the fact that profile completeness and a retry hint appear while the first match computation is pending. This is the kind of behavioral context annotations cannot supply.

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 purpose, then the routing cue, then pagination mechanics and exclusions; every sentence carries signal. The sentence about profile completeness and the retry hint is arguably redundant given an output schema exists, which keeps this just short of a 5.

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 a single optional parameter and an output schema, the description covers everything an agent needs: what it returns, the pagination protocol, what to do while computation is pending, and what side effects are impossible. No material gap remains.

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 parameter is already documented, which sets the baseline at 3. The description adds real meaning on top by stating the loop condition ("while next_cursor is not null, call again with cursor set to it"), clarifying how the cursor is actually consumed.

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 (read) and resource (personalized curated jobs) and enumerates the payload value: reasons, missing facts, application status. It is clearly distinguishable from list_applications, search_jobs, and get_job because it is explicitly the recommendation entry point.

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?

"Start here for recommendations" gives clear when-to-use guidance, and "Never starts an application or edits the profile" implicitly routes the agent away from apply_to_job and update_profile. It does not, however, name a sibling alternative for keyword-based job lookup, so the routing is implied rather than fully explicit.

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