Advance a flock by 1-1000 ticks and get its metrics back (polarization, cluster_count, mean_neighbor_distance), optionally with per-bird positions. An open question: freshly created flocks start disordered (polarization near 0.05). What is the earliest tick at which polarization first exceeds 0.5, and how does that ordering time scale with flock size n?
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes | ||
| flock_id | Yes | ||
| include_positions | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosure. It mentions advancing the flock and returning metrics, which implies state mutation, but it does not explicitly state that the operation is persistent, destructive, or requires permission. It also does not describe error behavior or edge cases like reaching maximum ticks, leaving some ambiguity about side effects.
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 concise with a clear first sentence; the second sentence introduces an open research question that adds context but is not strictly necessary for tool invocation. It is not overly long, and the structure is front-loaded with the operation, but the extra question slightly reduces focus.
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?
The tool has only 3 parameters and no output schema; the description lists the returned metrics and step range, which covers the main functional needs. However, it does not mention whether the flock state is permanently changed, how to handle invalid input, or how metrics are formatted, leaving some gaps for a simulation tool.
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?
The description adds semantics for steps ('1-1000 ticks') and include_positions ('per-bird positions'), but flock_id is not described beyond the schema. Since schema description coverage is 0%, it partially compensates but not fully, especially for the required identifier parameter.
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 the tool advances a flock by 1-1000 ticks and returns specific metrics (polarization, cluster_count, mean_neighbor_distance), optionally with positions. This specific verb+resource+scope distinguishes it from siblings like flock_create or flock_get, which create or retrieve states rather than stepping them.
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 open question about polarization ordering implies a use case (studying flock ordering over time), but there is no explicit guidance on when to use this tool vs alternatives, nor any mention of exclusions or prerequisites such as needing an existing flock. The usage context is only implied through the simulation question.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action: flock creation/querying/update/stepping/timeline, trace browsing/reading/leaving, and proposal browsing/submission. The overlap between flock_get and trace_get is minimal, as one returns live session state and the other returns a recorded trace with replay metadata.
All tools follow a consistent verb_noun pattern with lowercase and underscores: flock_create, flock_get, flock_set_params, flock_step, flock_timeline, trace_browse, trace_get, trace_leave, proposal_browse, proposal_submit. Even the longer flock_create_from_trace fits the pattern without deviation.
12 tools is well within the ideal range for a simulation playground. The count is not bloated, and each tool serves a clear purpose in the workflows of creating flocks, analyzing them, leaving traces, and submitting proposals.
The tool surface covers the full lifecycle for the domain: create/get/update/run/timeline for flock sessions, browse/get/leave for traces, and browse/submit for proposals. Discovery of existing sessions is possible through traces, and the playground_manifest provides orientation. No significant gaps or dead ends.