lira_press_dialog_button

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

With no annotations, the description carries the full burden and does well: it discloses the text-matching rules (case and '&' ignored), the disambiguation behavior for multiple dialogs, the return value ('the dialogs still shown'), and a concurrency caveat about other user-driven dialogs. It does not say what happens when no dialog or no matching button exists (error vs. no-op) or whether the call blocks waiting for a dialog.

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?

Four tight sentences with the action front-loaded and no filler; each sentence carries distinct information (matching, disambiguation, safety constraint, return value). The inline 'title:' label is slightly telegraphic but not wasteful.

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 and the description still usefully summarizes the return value as the dialogs still shown, so the agent knows the result is a dialog snapshot rather than a pressed-button confirmation. Combined with the matching and disambiguation rules, this is nearly complete; only failure/no-match behavior and blocking semantics are 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 description coverage is 0%, so the description must compensate and largely does: 'button' is defined as button text with normalization rules ('case and & ignored'), and 'title' is defined as a partial dialog title used for disambiguation. Minor gap: it never says 'title' is a substring match versus an exact match, though 'part of the dialog's title' implies substring.

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 (press a button of LIRA's dialog) and immediately qualifies it with the matching key ('by its text'), so the agent knows exactly what operation is performed and on what. Includes concrete literal examples ("OK", "Да", "Отмена") that make the resource tangible and distinguish it from the dialog-listing sibling.

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 when-not rule: 'Press only dialogs your own calls caused; the user may be answering others,' which prevents a real class of race conditions. Also explains when the optional title argument is needed ('needed when LIRA shows several'). It does not point to the sibling lira_dialogs as the way to discover what is on screen, so the alternative routing is implied rather than stated.

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