Find and Replace Text

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

With only destructiveHint=false in annotations, the description carries the behavioral burden and delivers: it discloses the non-obvious fact that block definitions are modified (so future inserts don't reintroduce old text), explains why DIMENSION is excluded (avoiding a broken association), and clarifies response semantics via searched_types. It does not explicitly flag that replacements permanently alter drawing content unless dry_run is used, which would justify 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?

Three sentences, with the core purpose front-loaded in sentence one and the two follow-ups earning their place: one explains block-definition behavior and response semantics, the other guards against a plausible misuse (DIMENSION). Prose is compact, though the middle sentence packs two distinct ideas into a dense form.

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 moderate-complexity tool with a full schema, an output schema, and a minimal but present annotation set, the description covers scope (types searched), a surprising side effect (block definitions), an exclusion (DIMENSION), and response-field intent. Little is missing for correct invocation; only an explicit irreversibility/preview warning would round it out.

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 100%, so the schema already documents all five parameters (find, replace, layer, dry_run, match_case). The description adds no per-parameter detail beyond what the schema provides, so the baseline 3 applies. The mention of searched_types concerns the response, not parameter semantics.

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 opening sentence uses a specific verb ('Replace') with a precise resource scope ('TEXT, MTEXT and block attributes (ATTRIB and ATTDEF)'), making the operation and target types unambiguous. The explicit enumeration of entity types distinguishes it from related siblings like entity_edit_text and text_set_background without needing to inspect them.

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 useful scope context: which entity types are covered, that block definitions are included, and that DIMENSION text is out of scope with a rationale. However, it stops at implied usage — it never names an alternative tool (e.g., entity_edit_text for single-text edits) or states an explicit condition for when to choose this tool over those alternatives.

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