ecosystem_trigger_debate

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

With no annotations provided, the description carries the full burden. It discloses that the tool performs validation (checks for architecture_done reviews), produces a suggested payload, and does not itself start the debate (explicitly notes Leader still calls debate_start). This sets clear expectations about side effects — that nothing is written until debate_start and ecosystem_link_debate_meeting are called. Missing: no mention of what happens on validation failure (does it error, return partial payload?), but the core behavior is well 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?

The description is reasonably compact for the complexity involved — three sentences covering purpose, validation, and follow-up sequence. The title line 'Stage 2' adds orchestration context. Could be tightened: the inline code formatting and follow-up sentence could be combined, but the structure is effective and front-loads the key purpose.

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?

This is a relatively complex staged tool (validate → build payload → hand off to debate_start → link meeting). The description captures the orchestration flow well and references the output schema (payload with topic + roles + review_ids). With an output schema present and 100% parameter coverage, the description adequately rounds out the picture. Missing: error/validation-failure behavior and what happens if a repo lacks architecture_done — whether it's skipped or errors.

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 100%, so the schema documents all 5 parameters thoroughly. The description does add context: it clarifies the parameters are 'suggested' and 'overridable at debate_start' for the judge/critic/advocate roles, and notes repo_ids are finalists selected from Stage 1. However, the description doesn't explain format constraints (e.g., repo_id format) or how research_goal influences topic generation beyond what the schema states. Baseline 3 is appropriate given full schema coverage.

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 clearly states it builds a debate dispatch payload, validates architecture_done reviews, and returns a payload for the caller to invoke debate_start. Verb+resource are specific and it distinguishes itself from debate_start (which it explicitly delegates to) and ecosystem_link_debate_meeting (which it names as the follow-up). Slight deduction because the core purpose — 'build a debate dispatch payload' — could be clearer about what debate dispatch means, but the follow-up sentences explain the mechanics.

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 provides clear context: it validates repo_ids have architecture_done reviews, then returns a payload for the caller to invoke debate_start. It also explicitly names the sequential relationship — first debate_start, then ecosystem_link_debate_meeting. This gives good when-to-use guidance distinguishing it from sibling tools. Deduction for not explicitly stating when NOT to use it or listing alternative dispatch paths.

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