search_and_replace

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

Beyond readOnlyHint=false, it discloses atomic saves with two-slot backup, the formatting-preservation guarantee across fragmented runs, regex capture-group refusal in live mode, and skipped slide-number/date fields. These are concrete side-effect and edge-case behaviors an agent cannot infer from 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 text is about 60 words yet covers purpose, safety, regex/live modes, backup, and sibling routing. It is front-loaded with the core operation and every clause adds 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 write tool with output schema available, it covers most invocation-relevant behaviors: locking, backup, formatting, and exclusions. The main gap is the scope parameter, whose semantics are not clarified, which keeps it from being fully complete.

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?

It adds meaningful behavior for regex (capture groups, refused live) and live (auto/force/off), and mentions the backup behavior. However, with 0% schema description coverage, the description still leaves several parameters unexplained, notably scope, and only implies match_case/include_notes from their names.

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 first clause, 'Deck-wide find and replace', names a specific verb and resource with clear scope, and the rest adds distinguishing traits (fragmented-run safety, SmartArt inclusion, excluded fields). It also points to set_table_cells and apply_edits as different tools, which separates it from nearby siblings.

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 explicit routing: bulk cell rewrites go to set_table_cells, batched edits go to apply_edits. It also defines the live parameter's three modes (auto/force/off) with the exact locked-file behavior, which tells an agent when to select each setting.

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