get_narrative[FORENSICS] Narrative heatmap for one asset: signal momentum, velocity, decay, manipulation probability and directional conviction across 1h / 4h / 24h windows — is the story building or dying? Complements get_mindshare_coin (attention share) with time-structure. Mirrors REST /narrative/{coin}. Analytical, not advice.
| Name | Required | Description | Default |
|---|---|---|---|
| coin | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true and openWorldHint=false. The description adds valuable behavioral context: it outputs a heatmap, focuses on time-structure (1h/4h/24h windows), and includes 'Analytical, not advice'. It also mentions it mirrors REST /narrative/{coin}, which is an extra detail beyond the 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 description is compact with four purposeful sentences: purpose and metrics, sibling relationship, API mapping, and an advisory note. Each sentence earns its place, though it is slightly longer than the high benchmark example.
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 read-only tool with a single parameter and no output schema, the description covers what it does, the metrics it provides, the time windows, and its relationship to another tool. It does not explicitly describe the return format, but the listed metrics give the agent a reasonable expectation of the output.
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 only provides a 'coin' string with no description. The description compensates by saying 'for one asset' and 'Mirrors REST /narrative/{coin}', making it clear that the coin parameter is the asset identifier. This adds meaning despite 0% 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 clearly states it is a 'Narrative heatmap for one asset' with specific metrics (signal momentum, velocity, decay, manipulation probability, directional conviction) across time windows. It distinguishes itself from get_mindshare_coin by focusing on time-structure, making its purpose 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 explicitly says 'Complements get_mindshare_coin (attention share) with time-structure', guiding the agent on when to use this tool versus its sibling. It also adds 'Analytical, not advice' as an interpretive caveat. However, it does not explicitly state exclusions or conditions when not to use it.
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 have clearly distinct purposes with detailed descriptions, but there are clusters of similar concepts (e.g., get_liquidity_map vs get_liquidation_map, get_state vs get_state_brief, multiple signal-related tools) that could cause misselection despite thorough documentation.
All tools follow a consistent lowercase verb_noun pattern, predominantly get_* nouns, with only a few non-get verbs like list_signals, rank_trades, log_trade, etc., but the style is uniform.
With 52 tools, the surface is extremely heavy for an agent to navigate. While the server's scope is broad, the count far exceeds the typical 3-15 range and falls into the 'too many' category.
The tool set covers the full lifecycle for journaling, signals, market analysis, and proof, with no major dead ends. Minor gaps exist, such as no dedicated get_trade_by_id (workaround via get_journal) and no get_market_state tool despite being referenced in get_state.