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

Annotations already establish read-only/idempotent/non-destructive, and the description still adds real behavioral context: days defaults to 45 with a 120 cap, since overrides days and reaches back at most 120 days, the reply ends with total and next_page, and employees_min keeps unknown-headcount companies ranked last. new_since_last_pull is explained as per-account, per-filter-set server state that ignores page and requires a signed-in account — the kind of detail an agent cannot 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?

It is front-loaded with what the tool returns, which is good, but it drifts into a dense run-on filter inventory that duplicates schema content (the full signals list, the department alias rule, the OR-joining example). Several clauses could be trimmed without losing selection-relevant information.

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 26 optional parameters and no output schema, the description does the necessary work: it defines the two result shapes, pagination, the days/since interaction, and the stateful new_since_last_pull loop. What remains thin is the meaning of some sort_by modes (intent, warm_intro) and the 'intent score and why' output, but overall an agent can call this correctly.

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 earns a bump by explaining semantics the schema cannot: why title_family beats a literal keyword (titles vary across companies) and how department aliasing behaves. It also restates signals and the department alias that the schema already covers, which dilutes the added value slightly.

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 ('companies hiring right now from their live job postings') and enumerates the payload per card (open-role counts, sample roles, signals, intent score, funding, leadership change). The two views ('companies' vs 'postings') are defined explicitly. It never names or distinguishes itself from the nearest sibling, search_raised_and_hiring, so an agent must infer that edge case.

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?

Strong prescriptive guidance: use title_family rather than a single keyword for leadership roles, keyword accepts ' OR '/'|' joined titles, department 'Sales' expands to GTM/Revenue/Business Development. These are explicit when/how instructions with an anti-pattern called out. It stops short of saying when to pick this tool over sibling searches (search_raised_and_hiring, get_daily_leads).

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