atlas7_field_catalogSubscription-gated field, metric, filter, sort, and evidence contract for one governed semantic model.
| Name | Required | Description | Default |
|---|---|---|---|
| model_key | Yes | Required governed semantic model key. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context not in annotations by indicating the tool is 'Subscription-gated', which implies access control requirements. It also scopes the operation to a single governed model. Annotations already declare readOnlyHint and destructiveHint, so the additional context is valuable but not exhaustive.
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 a single, compact sentence with no redundancy. It front-loads key qualifiers ('Subscription-gated') and lists the catalog types efficiently, making every word useful.
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?
Given the tool's simplicity (one parameter) and the presence of an output schema, the description is largely complete. However, terms like 'evidence contract' are not explained, and subscription-gating details are vague, though these are minor given the supporting structured data.
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 schema fully covers the single parameter model_key with a description. The description's phrase 'one governed semantic model' aligns with this parameter but does not add new meaning or syntax details beyond what the schema already provides. Baseline 3 applies due to high 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 explains the tool's scope—field, metric, filter, sort, and evidence contract for one governed semantic model—which expands on the title. It does not use an explicit verb like 'retrieve' or 'list', but the title's 'catalog' implies this. It distinguishes from siblings like atlas7_model_catalog by specifying 'for one governed semantic model'.
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 does not state when to use this tool versus alternatives such as atlas7_model_catalog or atlas7_semantic_query. It only implies usage for a governed semantic model, with no explicit when-to-use, when-not-to-use, or alternative comparisons.
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.
The tool set has extensive overlap: natural-language variants duplicate raw JSON tools (e.g., deltasignal_covenant_stress vs deltasignal_covenant_stress_natural), composite workflow tools duplicate low-level screens (deltasignal_alpha_sweep vs deltasignal_alpha_opportunities), and the atlas7_* and deltasignal_* prefixes repeat the same concepts (e.g., atlas7_covenant_stress vs deltasignal_covenant_stress). An agent would likely struggle to pick the right tool for a given intent.
Three distinct prefixes (atlas7_, deltasignal_, strategix_) are used, and duplicate tool names appear across prefixes (e.g., atlas7_readiness vs deltasignal_readiness). Verb patterns are inconsistent, mixing nouns and verbs (atlas7_archive_search, deltasignal_thesis_create, deltasignal_morning_brief_natural), and there is no clear rule for raw, natural, composite, or resolver variants.
With 81 tools, the server is massively over-scoped. Many are near-duplicates or overlapping composites; the core domain likely needs 20-30 tools at most. The count is far beyond what an agent can reasonably navigate, and it indicates a failure to consolidate or version the surface.
The set covers a broad range of functionality: screening, stress, alpha, peer comparison, history, tripcode resolution, synthetic ETF state, and thesis monitoring. However, there are lifecycle gaps (e.g., thesis_create has no corresponding update/delete, and the atlas7 vs deltasignal split leaves no unified surface). The duplication suggests comprehensive coverage in some areas and awkward holes in others.