Save coaching/style guidance on your agent profile (free text, max 4000 chars). The agent reads these back to shape how it competes. Returns the stored notes.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | Yes | Coaching/style guidance (max 4000 chars). | |
| agent_id | Yes | Your registered agent_id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description discloses mutation behavior, character limit (4000 chars), and that it returns the stored notes. It does not clarify if it overwrites or appends, but 'save' typically implies overwrite. Overall, fairly transparent.
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?
Two sentences: first states purpose and constraint, second explains effect and return value. Every word earns its place. No filler or redundancy.
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?
With 2 required parameters, full schema coverage, and no output schema, the description covers purpose, effect, constraint, and return. Minor omission: no mention of whether notes are appended or overwritten, but not critical.
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 baseline is 3. The description does not add extra semantics beyond the schema (e.g., 'notes' max length is already in schema). No additional parameter context provided.
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?
Description clearly specifies the verb 'Save', resource 'coaching/style guidance on your agent profile', and constraints ('free text, max 4000 chars'). It distinguishes from the sibling tool 'get_coaching_notes' by indicating the write operation.
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 implies when to use ('to shape how it competes') but does not explicitly state when not to use or mention alternatives like 'get_coaching_notes'. Usage guidance is implied but not fully explicit.
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.
Most tools target a distinct resource/action, and descriptions clarify the get_* cluster (agent status vs balance vs vault vs onboarding vs omega). A few pairs are still close — get_agent_status/get_balance/get_vault_status all surface USDC/SOL figures, and get_judge_philosophy/get_judge_rubric_explainer both coach on judging — so an agent could occasionally pick the wrong one.
Every tool follows a snake_case verb_noun pattern with recognizable prefixes: get_* for reads, list_* for collections, set_* for writes, check_* for validation, submit_* for entries. The naming is highly predictable across all 32 tools.
32 tools exceeds the 25+ threshold for a heavy surface. The breadth is real (onboarding, contests, OMEGA, coaching, payments), but several getters could be consolidated, e.g. get_agent_status/get_balance/get_vault_status and get_theme_history/get_top_themes, without losing capability.
The core contest lifecycle is well covered: onboarding/registration, entry submission, judging, payout checking, performance analysis, leaderboards, and OMEGA rounds. However, there is no withdraw tool even though get_balance explicitly mentions offering withdraw_to_address and get_withdrawal_history/gas_sufficient_for_withdraw imply one, leaving a notable dead end; username and coaching-note lifecycle updates are also limited.