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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is known. The description adds genuinely non-structured context: the cost model (managing free; scrapes, jobs, queries and monitor runs bill credits), the validation contract (a wrong field is refused free), and the dry-run preview semantics. It stops short of 5 because it never explains what a delete or pause actually destroys, nor idempotency-key semantics beyond the 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?

It front-loads the area taxonomy before cost and dry-run details, and packs a lot of operational guidance into roughly three sentences. The trailing fragment 'rows_new alerts need track (id=monitors)' is terse and somewhat cryptic, but overall the text is dense rather than padded.

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 complex four-area dispatcher with no output schema, the description covers the area map, cost model, dry-run and validation. It omits how async actions are chained (e.g. polling query_status or job_get) and what the actions return, so it is helpful but not fully self-sufficient.

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 high (83%), so the baseline is 3, and the schema covers area/action/id/input/idempotencyKey. The description adds real value on top by defining dry_run behavior in prose (the schema leaves dry_run undescribed) and by hinting at the shape of the input payload. It does not clarify the idempotencyKey usage windows, which keeps it at 4.

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 gives a concrete verb (manage) plus a resource taxonomy, enumerating the four areas and what each covers (monitors = scheduled recipes/webhooks/alerts, cohorts = mention search on your panel, web = scrape/search/crawl/agent jobs/sessions, jobs = Prism background jobs). This is far more specific than the vague name 'socialcrawl_manage'. It does not, however, distinguish itself from siblings like socialcrawl_collect or socialcrawl_find, so it stops short of a 5.

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 provides conditional guidance for one path ('dry_run: true validates and quotes a create/update and never creates it') and one cross-tool pointer ('rows_new alerts need track (id=monitors)'), and it notes that managing is free while operations bill credits. But it never states when to prefer this tool over socialcrawl_collect, socialcrawl_estimate or socialcrawl_request, so usage is largely implied by the area breakdown rather than explicitly routed.

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