gex-mcp

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, lowering the bar. The description adds useful context beyond those hints by enumerating the specific contents (zero-gamma flip, call resistance, put support, hold band) and the 'finished session' constraint, which clarifies that intraday sessions are not applicable.

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, well-structured sentence that front-loads the tool's purpose and details. Every word earns its place, with no redundancy or filler.

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 simple single-parameter interface and the read-only nature, the description is complete. It enumerates all the return components an agent would need to know, and the absence of an output schema is compensated by this explicit listing.

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 input schema fully covers the single parameter 'day' with format description 'YYYY-MM-DD'. The tool description does not add further meaning or constraints beyond what the schema already provides. Per the baseline for >80% schema coverage, a score of 3 is appropriate.

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 states exactly what the tool returns: the dealer-positioning level set for a finished SPX session, including zero-gamma flip, call resistance, put support, hold band, and the session close relative to them. This clearly distinguishes it from sibling tools like get_session (which likely returns broader session data) and list_sessions (which lists sessions).

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 implies its use when dealer-positioning levels are needed, but it does not explicitly name alternatives or state when to use get_session or list_sessions instead. There is no explicit 'when/when-not' guidance, only an implied scope via 'Just the dealer-positioning level set.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, and the description adds valuable context: it is 'measurements only' with 'no buy/sell signals,' and it refers to a 'finished' session, implying historical data. This clarifies the tool's non-predictive, factual nature beyond what annotations disclose.

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 two sentences, front-loaded with the tool's purpose and a list of included data, followed by a concise caveat about lacking signals. Every word serves a purpose, with no redundancy or unnecessary detail.

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?

With no output schema, the description explains the return contents by enumerating specific data fields (OHLC, zero-gamma flip, call/put walls, hold band, etc.). It also mentions the source (gex.live) and the scope (one finished session), making it sufficiently complete for agent use.

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 descriptions fully cover the single parameter 'day' with format YYYY-MM-DD. The description does not add additional parameter semantics beyond implying the day should be a finished session, so the baseline score of 3 applies with no extra value added.

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 provides a dealer-positioning summary for one finished SPX session, listing specific metrics (OHLC, zero-gamma flip, call/put walls, hold band, net-gamma percentile, ATM IV). This specific verb+resource+scope distinguishes it from siblings like list_sessions (which likely lists sessions) and get_levels (which likely provides level 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 when to use this tool: for a single finished session's summary data. It does not explicitly contrast with alternatives like get_levels or list_sessions, nor does it provide exclusions, but the 'one finished session' qualifier provides clear context for appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. The description adds useful behavioral details: only 'finished' sessions are listed, they are ordered 'newest first', and data is free to access. It does not cover pagination or return structure, but what is added goes 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 two sentences with no fluff: the first states the core purpose and ordering, the second connects to related tools and free access. Every word earns its place and the most important information is front-loaded.

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 list tool with one optional parameter and no output schema, the description is sufficiently complete. It tells the agent what is listed, the ordering, and how to proceed with the results via sibling tools. No critical usage aspect is missing.

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 100% for the single 'limit' parameter, which has its own description in the schema. The tool description does not mention the parameter, so it adds no extra semantics. Baseline 3 is appropriate because the schema fully documents it.

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?

Clearly states the verb 'List' and the resource 'finished SPX trading sessions' with specific source 'free gex.live archive' and ordering 'newest first'. This distinguishes it from siblings get_session and get_levels, which fetch specific 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 says 'Every listed day can be fetched with get_session / get_levels', implying this tool is the entry point for discovering available sessions before fetching details. However, it does not explicitly state when not to use it or provide alternative comparison, so slightly below the explicit standard.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.