Delimit Swarm

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

The annotations (readOnlyHint=false, destructiveHint=false) only signal that the tool mutates and is not destructive. The description adds a Side effects section that classifies which action classes mutate (register/create_tool/create_agent/approve_agent/reload) versus which are read-only (status/venture/agent/list_*/check/approve/guide/rules) — genuinely useful beyond the annotations. Minor deductions: 'approve' appears in the read-only list while 'approve_agent' is in the mutation list, creating slight ambiguity, and permission requirements are not disclosed.

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?

Well-structured with labeled sections: purpose sentence, when to use, when not to use, sibling contrast, side effects, and a venture-structure note. The purpose is front-loaded and every section earns its place. Slightly long, but the length is justified by the tool's polymorphic action surface with 14+ action values.

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 high-complexity tool (7 optional parameters, polymorphic action, no enums), the description covers the critical decisions: when to use it, which actions mutate state, and how it differs from the per-task sibling. Output schema presence relieves it of explaining return values. Remaining gaps: it never states that calling with no arguments defaults to action='status', and the action-specific parameter roles rely on the schema's terse hints ('for register/venture/create_agent').

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 the extra point by supplying the vocabulary for the polymorphic action parameter — the schema's own action field defers to it ('See actions above') — and by enumerating access_action values (read/write/deploy; deploy_production/deploy_staging/social_post). It does not fully resolve ambiguous parameters like repo_path ('description, or reason depending on action'), but the schema's per-parameter hints cover most of the remaining meaning.

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?

Opens with a specific verb-resource pairing ('Manage the cross-venture agent swarm') and enumerates concrete capabilities (register a venture with its 5 agent roles, create custom tools, hot-reload modules, check namespace access). It distinguishes itself from delimit_agent_dispatch, which the description explicitly labels as per-task, so an agent can separate the two without opening schemas.

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?

Contains explicit 'When to use' and 'When NOT to use' sections, the latter naming exact alternatives (delimit_agent_dispatch for single-task dispatch; delimit_agent_status / dashboard for agent state). Adds a sibling contrast line and even cites the governing standard (Agent Swarm Standard v1.2). This is complete routing guidance, not merely implied context.

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