peersThe stock's TRUE competitive cluster — LLM-curated from segment overlap (who it actually competes with for revenue), not GICS classification. Costco's peers are WMT/TGT/KR, not 'Discount Stores'. Each peer carries its P3 score. Honest empty list for monopolies/private-rival cases.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true and destructiveHint=false. The description adds meaningful behavior beyond that: results are LLM-curated from segment overlap, each peer carries a P3 score, and monopolies/private-rival cases yield an honest empty list. These are non-obvious edge-case and methodology disclosures.
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?
Three sentences carry dense, relevant information: methodology, a concrete example, output score details, and empty-list behavior. There is no filler; every sentence earns its place.
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 single-parameter read-only list tool with no output schema, the description covers the core output (peers with P3 scores) and the empty case. It does not specify the exact response envelope or peer object shape, but the expected usage is clear enough for an agent to act on.
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 coverage is 0% and the only parameter, ticker, has no schema description. The description implies the input is a stock ticker via 'The stock's' and the Costco example, but it never explicitly explains the expected format, ticker universe, or invalid-input behavior.
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 identifies the tool's output as the stock's competitive cluster ('TRUE competitive cluster') and distinguishes it from GICS classification with the Costco example. It lacks an explicit verb like 'returns' or 'lists', but the resource and method are unambiguous.
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 gives clear context for when to use the tool: when you need the actual revenue-competitor set, not the GICS sector. It also discloses the empty-list behavior for monopolies and private-rival cases. It does not explicitly name sibling alternatives or exclusions, so it stops short of the highest score.
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 owns a distinct analytical niche: single-stock character, multi-ticker comparison, market regime, business peers, co-movement cluster, and universe screening. The only near-overlap (fingerprint's peer list vs peers) is explicitly resolved by describing peers as the deeper standalone lookup.
All names are lowercase and stylistically consistent, but there is no verb_noun pattern: compare and screen are verbs while market_regime, peers, and theme_cluster are noun phrases. The mixed grammar is readable but not a strongly predictable naming convention.
Six tools is tightly scoped for a stock-character research server; each tool covers a distinct user workflow and none feels redundant. The count is well within the ideal range and does not burden an agent with overlapping endpoints.
The set covers the full intended workflow: assess market context, inspect a single stock, compare tickers, identify true peers and co-movement groups, and screen the universe on every available metric. There are no obvious dead ends or missing operations for a read-only analytics domain.