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

Annotations already flag destructive=true, readOnly=false, and openWorld=true, but the description adds critical context beyond that: it spends Credits up to max_credits, the Space owner pays, a linked agent spends its person's Credits and requires a grant, public posts cannot be removed, and request text is not privacy-checked. These are exactly the kind of consequential behavioral details an agent needs before invoking a destructive, open-world mutation.

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 front-loaded with purpose and is dense with useful rules, but it becomes a long, run-on block. Some material repeats what is already in the schema descriptions (retention, max_credits, destination_space_id), and the agent-type definitions are lengthy; the content mostly earns its place, but structure and duplication could be improved.

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?

Given the complexity (14 parameters, nested objects, output schema present, destructive annotations present), the description covers the high-risk areas: credits/spending, disclosure/consent, public thread irreversibility, write destinations, and authentication requirements. It omits a few lesser parameters, but nothing critical for correct invocation 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 coverage is only 43%, so the description must do substantial work, and it does: it explains read_space_ids versus discussion.public_read_space_ids, the dual role of public_post_space_ids, write/destination semantics, retention behavior, max_credits defaults, and timeout_seconds limits. It does not cover every parameter (e.g., accepted_rate_card, cross_space_disclosure, public_research_queries), which keeps it from a 5.

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 and resource: 'Launch one internal agent, chosen by agent, on selected Spaces.' It names the four agent variants and clearly distinguishes this from task-reading tools by pointing to task_get. The agent can immediately tell this is a launching/mutation tool, not a query tool.

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 gives explicit routing guidance: use task_get to read the Task deliverable, use agent_grant_set for linked-agent grants, choose exactly one write Space automatically for Curator or findings/session, and use public read/posting fields for public threads. It also explains the four agent roles in enough detail for an agent to select the right one. There is very little inferential burden left.

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