Read recent rows from the polymorphic audit log: outcome, shape, counterparty hash, token id, revenue. Anonymized counterparty (hashed). No auth.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows to return (default 50, max 500) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that counterparty data is anonymized via hashing and that no authentication is required, which are critical behavioral traits for an agent. The 'Read' verb clarifies it is non-mutating, though it doesn't detail pagination or error behavior. This is adequate given the lack of annotations.
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 entire description is a single sentence that packs purpose, fields, privacy handling, and auth requirements. No filler words or repetition.
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 simple read tool with one parameter and no output schema, the description covers the key aspects: what it reads, what fields are returned, and important caveats (hashing, no auth). It does not explain 'polymorphic audit log' but the sibling tool names and context make it sufficiently clear.
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 only parameter, limit, is fully documented in the schema with default and max values, achieving 100% schema coverage. The description adds no additional parameter-level detail, so the baseline score of 3 applies.
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 'Read recent rows from the polymorphic audit log' which clearly specifies the verb (read), resource (audit log), and scope (recent rows). It also lists the specific fields returned, distinguishing it from sibling tools like morph_brood_all that likely return broader brood data.
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 clearly implies usage for retrieving recent audit log entries, with 'recent' suggesting time-bound reads. It doesn't explicitly name alternatives or state when not to use, but the specific resource and field list provide enough context for an agent to select it appropriately.
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 distinct resources (broods, supermodels, money flavor, audit, carousel). The pair morph_money_flavor_probe and morph_money_flavor_stats are close but distinguished by scope (latest window vs rolling stats). Similarly, morph_brood_conversion and morph_brood_conversion_leaderboard are related but serve different purposes. Overall, minimal overlap.
All tools share the 'morph_' prefix, but the structure after is inconsistent: some use verb+noun (morph_get_identity, morph_list_supermodels), others use noun+descriptor (morph_brood_conversion, morph_money_flavor_probe), and some are just nouns (morph_carousel). This mixed convention makes the naming pattern less predictable.
With 14 tools, the count is appropriate for the server's broad scope covering supermodels, broods, money flavor, audit, and scans. Each tool has a distinct purpose, and the number is within the ideal range.
The server provides comprehensive read-only coverage for analytics: listing/fetching supermodels, brood conversion metrics, audit logs, money flavor stats, and dry-run scans. However, it lacks write operations or a way to act on pending approvals, which may be intentional but leaves a gap for full lifecycle management.