Skip to main content
Glama

tokscale_competitive_intel

Read-only

Benchmark a specific AI tool by passing its tokscale slug to receive its token rank, usage profile, and head-to-head comparisons against every competitor.

Instructions

Competitive intelligence for any AI tool company. Pass a target tool (by tokscale client slug like 'claude', 'codex', 'devin-cli' or canonical platform name like 'devin', 'other') and get: the target's rank by tokens among all detected tools, its full profile (tokens, cost, model mix, cache_read_pct, cost_per_million_tokens, market share), and a head-to-head comparison against every competitor (each competitor's tokens, cost, model_count, share, cost_per_million_tokens). Returns market_totals for context. If the target is not found, lists all detected clients. Use this to benchmark one AI tool against its competitors on this machine. All data is local — this is your own usage, not aggregate market data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
targetYesThe AI tool to analyze. Accepts a tokscale client slug (e.g. 'claude', 'codex', 'devin-cli', 'copilot') or a canonical platform name (e.g. 'devin', 'claude', 'other'). Case-insensitive. To discover valid slugs, call tokscale_market_share first.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent if tokscale is unavailable or target is empty
foundNoWhether the target was found in local data
targetNoThe resolved target slug(s)
competitorsNoAll other detected tools with comparison metrics
market_totalsNoAggregate market context: { tokens, cost, messages, tool_count }
rank_by_tokensNoTarget's rank among all detected tools by token volume
target_profileNoTarget's full usage profile with model mix and market share
Behavior4/5

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

The description discloses that all data is local (own usage, not aggregate) and explains fallback behavior (lists clients if target not found). ReadOnlyHint is already true, so no contradiction. Adds useful context about scope and data source.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single informative paragraph with no wasted words. It could be slightly more structured (e.g., bullet points), but it is concise and front-loaded with purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given only one parameter, complete schema coverage, and an output schema (not shown but exists), the description covers all needed context: input format, return data details, fallback behavior, and data source. It is fully adequate for correct tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'target' is fully described: it accepts client slugs or canonical names, case-insensitive, and the description provides examples and suggests discovering valid slugs via another tool. This adds significant meaning beyond the schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides competitive intelligence for any AI tool company, specifying that you pass a target tool and it returns rank, full profile, head-to-head comparisons, and market totals. It distinguishes from siblings by focusing on single-tool benchmarking against competitors using local usage data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use (to benchmark one AI tool against competitors) and what happens if target not found (lists all detected clients). It suggests calling tokscale_market_share for valid slugs. However, it does not explicitly state when not to use or provide alternatives to other siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SunrisesIllNeverSee/sigrank-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server