Live mempool stats: pending tx count, total size in vbytes, total fees in BTC.
High pending count (>200K) = congestion. Low count (<50K) = quiet.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the specific stats and units (vbytes, BTC) and gives advisory thresholds, which is helpful. However, it does not mention data source, caching behavior, or whether stats are cumulative, which are useful for a read tool. The transparency is adequate but not rich.
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 exceptionally concise, with a clear front-loaded summary of the three main stats, followed by a brief, useful interpretive note. Every sentence provides value and there is no redundant phrasing.
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 stateless, parameterless tool, the description sufficiently covers the output fields and basic interpretation. The presence of an output schema means return values don't need detailing. However, the lack of usage guidance and any mention of 'live' semantics or update frequency leaves minor gaps for a complete picture.
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?
There are zero parameters, so parameter semantics are trivially covered by the empty schema. The baseline for 0 params is 4, and the description does not need to add anything beyond what is already given. It correctly identifies the tool's self-contained nature.
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 the tool provides live mempool stats including pending transaction count, total size in vbytes, and total fees in BTC. This is a specific verb+resource combination and effectively distinguishes it from sibling tools like get_mempool_fees, which likely focuses on fee details.
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?
No guidance is given on when to use this tool versus alternatives such as get_mempool_fees or get_dashboard. The description only provides interpretive thresholds for congestion/quiet, not usage context. It does not mislead but offers no comparative direction.
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.
Tools like get_convergence, get_directional_bias, and get_dashboard are related but clearly scoped: convergence checks sensor agreement, directional_bias gives the trade call, dashboard bundles everything. Mempool fees vs stats are distinct (rates vs pending tx). Some overlap exists between convergence/regime_current, but descriptions disambiguate well.
All tools follow a consistent get_verb_noun pattern (get_block_tip, get_funding_divergence, get_system_health). The only exception is query_db, which uses 'query' instead of 'get', but it still follows the verb_noun structure and same snake_case style. No mixed conventions.
15 tools is at the high end of the ideal range, but each serves a distinct function in a complex domain: sensor convergence, regime, funding, gamma, mempool, system health, audit. The Pro/free tier adds some apparent duplication (get_convergence vs get_directional_bias), but they address different questions.
The tool set covers the full workflow: convergence check, directional call, regime context, specialized indicators (funding, gamma, stablecoin flows, fee histogram), mempool data, system health, audit trail, and a queryable database. No obvious dead ends; public signal history and counters support verification.