write_tester_config

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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds genuine value by disclosing two hard-coded settings (ShutdownTerminal=1, Visual=0) that the agent could not otherwise predict. It does not disclose file-overwrite behavior, where the file is written when path is omitted, or that openWorldHint=true implies writing outside a sandbox.

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?

Three short sentences with the fixed-value constraints front-loaded and no filler. The line-broken formatting is slightly awkward but nothing is wasted.

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 13-parameter write tool with no output schema and no parameter descriptions, the description is far too thin — most fields an agent must fill (dates, deposit, leverage, optimization, period) are left to guesswork. It is adequate only for the two required fields plus model selection.

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 description coverage is 0% across 13 parameters, so the description carries the full burden, yet it explains only model, source, and inputs. Critically, it supplies the four valid model values (every_tick, ohlc, open_prices, real_ticks) that the schema lacks an enum for — high value. But expert, symbol, period, date_from, date_to, deposit, currency, leverage, optimization, and path remain entirely undocumented, including format expectations for the date strings.

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?

"Write a headless tester.ini" is a specific verb plus concrete artifact, so the agent knows this produces a configuration file rather than executing a backtest. It is distinguishable from run_backtest and read_inputs by implication, though it never names a sibling explicitly.

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 gives real guidance for choosing between the two input mechanisms ("Pass source to seed TesterInputs from the EA, or pass inputs as a name-to-value map"). It says nothing about when in the workflow this should be called relative to run_backtest, or whether an existing tester.ini is overwritten.

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