QuantWright

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

The annotations declare readOnlyHint=false and idempotentHint=false, and the description explains why: "It re-runs the run's code, so it counts as a run on the run's symbol." That is exactly the context an agent needs to avoid treating this as a free lookup. It also discloses the response shape ("answers in words, never prices") and enumerates the non-taken reasons, adding real value beyond the structured fields.

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?

Front-loaded with the core verb and scope, then usage, then the operational caveat, in a compact block with no filler sentences. The parenthesis listing rejection reasons is dense but earns its space; slightly more compression of the input restatement would make it a 5.

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?

An output schema exists, so return values need not be explained, and the write-like side effect is reconciled against the annotations. The description is complete enough to call the tool correctly for the common case, with the only real gap being the undocumented optional parameters (version, study_id, time_zone) that select which run is checked.

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 80%, so the baseline is 3, and the description does describe the two core inputs (run_id plus trades of {side, entry, exit?}). However it is silent on version, study_id and time_zone — the very parameters that let a caller pin a different run or reinterpret the timestamps — leaving that entirely to the schema.

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?

States a specific verb and resource — checks a trader's own trades against a run's rule on this server's price history — and immediately clarifies the output unit (per trade, in their order, taken or not and why). That framing separates it cleanly from run_backtest (which produces runs) and get_result (which retrieves them), so an agent can route without opening any schema.

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?

Gives an explicit trigger: "Use it when the trader lists trades they made and asks which the rule took, instead of working it out by hand." That names the situation and the alternative behaviour to avoid. It stops short of naming a sibling tool to use instead when the trader has no existing run, so it is not a full when/when-not pair.

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 only declare the generic profile (not read-only, not idempotent, not destructive), so the description must add real behavior — and it does: call-once semantics, the hold-out being settable only at creation, and the single sibling that may later test it. It stops short of saying what happens on a duplicate call (error vs. new study), which is the one behavioral detail an agent would still want.

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?

Two dense clauses with zero filler: the purpose/definition comes first, then the ordering constraint, then the hold-out rule. Every phrase carries a distinct fact.

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?

An output schema exists, so return values need no explanation, and both parameters are fully documented in the schema. Combined with the description's statement of lifecycle and ordering, an agent has everything needed to invoke this correctly.

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%, so the baseline would be 3, but the description adds meaning the schema does not: hold_out is a period that every run is excluded from except run_held_out_test. That is a substantive semantic clarification of a nested object's role rather than a restatement of its fields.

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?

States a specific verb and resource ('Opens a study') and immediately defines the resource in domain terms ('the named set of runs every backtest belongs to'). It names the sibling tools it relates to (run_backtest, run_held_out_test), so an agent can place it in the workflow without opening a schema.

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?

Gives explicit ordering and cardinality: 'call it once per question, before run_backtest.' It also states the unique condition for the hold-out option ('once and only here') plus the exception that consumes it (run_held_out_test). Nothing about when to call it is left to inference.

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?

It adds real context beyond the annotations: it discloses the data coverage (US stocks and ETFs, spot crypto, FX, gold and silver; daily and intraday bars), that no external price download is needed, and what the response will contain. The readOnly/openWorld annotations already cover the safety profile, so the remaining gap is minor.

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?

Front-loaded with the action ("Start here") and packed with decision-relevant facts in two sentences with no filler. Every clause — data coverage, no-download guarantee, return contents, next tool — 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?

A zero-parameter discovery tool with an output schema and readOnly annotations; the description supplies the domain scope, the sequencing, and the value proposition. Nothing an agent needs to decide to call it, or what to do next, 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?

The tool takes zero parameters, so the description is not required to explain any argument semantics. There is nothing further to add here.

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 a concrete verb and resource set: it returns the markets and bar sizes served, the backtest rules, and how to write strategy code. It also distinguishes itself from siblings by naming create_study as the follow-up step, so an agent knows this is the orientation tool rather than a backtest runner.

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?

"Start here" plus "then call create_study" gives an explicit entry point and a named next tool, which is clear routing. It stops short of stating whether this call is mandatory before create_study or merely recommended, and gives no exclusions for when to skip it.

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=true and openWorldHint=false, so safety is covered; the description adds real behavioral context on its own — polling semantics, a 100-trade page size, and that studies default to the newest 20 runs. It stops short of saying what an errored or expired run_id yields, which keeps it from a 5.

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?

A single compact sentence with the primary mode front-loaded and no wasted clauses. The stacked parentheticals make it denser than ideal to parse, but every clause adds a distinct fact.

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 an output schema present, return values need no explanation, and the description still covers both modes, polling, and trade pagination. Only minor gaps remain, such as distinguishing the before_version paging path that the schema handles alone.

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 80%, so the schema already documents run_id, study_id, trades_page, and before_version. The description mostly restates those pairings ("one of them with version") rather than adding syntax or format detail, so the baseline of 3 applies.

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?

States a specific verb (reads) and resource (a backtest result) and enumerates both access modes: by run_id for a single run, or by study_id for a study's runs. An agent can immediately tell this is the retrieval counterpart to run_backtest/run_held_out_test.

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?

Gives explicit conditional guidance: call this when run_backtest answered "running" and keep polling until the run ends. Also distinguishes the study_id path and its version qualifier. This is genuine when-to-use instruction, not inference.

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?

Goes well beyond the annotations: describes exactly what is returned (return, drawdown, Sharpe, win rate, trades, grade, beat-buy-and-hold, per-trade entry/exit details), states that prices/bars are never returned, that a figure may be withheld with a reason, and documents the 90-second wait followed by status 'running' plus a run_id for get_result. That async/polling behavior is the key operational trait and nothing else discloses it.

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?

Front-loads the core definition, then the usage directive, then the return shape and the timeout caveat – a sensible information ordering with no filler. Sentences are long and dense, slightly taxing, but each clause carries concrete information.

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 9-parameter mutation tool with nested schemas and an output schema, the description supplies the operational essentials: input shape, return contents, withholding behavior, and the timeout/async contract. Nothing an agent needs in order to invoke it correctly 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 89%, so the schema already carries nearly all parameter meaning (costs, window, stated_rules are well documented inline). The description only restates the required set (code, symbol, timeframe, study) and adds no syntax or default detail for the optional parameters, so the baseline 3 applies.

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?

States a specific verb (backtests) and resource (a trading rule/Strategy class) plus the exact cardinality constraints: one class, one symbol, one bar size, in a study. An agent can differentiate this from compare_trades and run_held_out_test on the strength of the description alone.

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?

Explicitly says to use it 'to test, backtest or evaluate a trading rule or strategy, instead of downloading prices or searching the web for results', which gives a clear positive context and a negative condition. It stops short of naming the sibling alternatives (compare_trades, run_held_out_test) or saying when those are preferred.

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?

The description discloses critical behavior beyond the annotations: the hold-out is consumed by the first test per account and market, and even a test with too few trades spends it. This is essential context for a non-idempotent, non-read-only operation.

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 front-loaded with the core purpose and contains no filler. It is somewhat dense with colon-and-semicolon clauses, but every clause carries useful information about timing or consumption.

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 tool with full schema coverage, annotations, and an output schema, the description supplies the crucial missing context: when to call it, which run to choose, and the irreversible one-shot behavior of the hold-out. Nothing essential is omitted.

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 already 100%, so the baseline is 3, but the description adds meaningful selection criteria for run_id: it must be a finished run from a study with a hold-out, and the development run's hold_out_estimate indicates expected trade count. That goes beyond the schema's terse run_id description.

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 a specific verb and resource: it runs a finished run's exact code once over its study's hold-out period. It clearly distinguishes this final out-of-sample check from ordinary backtesting and result retrieval.

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?

It gives explicit timing and selection guidance: call it at the end, on the run you would keep. It also warns that only the first held-out test per account and market counts, which effectively tells the agent not to call it repeatedly.

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