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

The annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new context: 'one bounded' edit implies a single occurrence by default, and 'exact revision guard' discloses optimistic concurrency semantics that are not in the annotations. It doesn't explain what happens on a revision mismatch, 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?

Two sentences with zero filler. The core operation is front-loaded, followed immediately by the safety prerequisites, so the agent gets the critical constraints before opening the schema.

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?

Output schema exists, so return values needn't be explained. However, for a destructive mutation with 0% parameter documentation, the description should cover replaceAll semantics, idempotency behavior, and what a revision-guard failure looks like. It covers the destructive/confirmation side adequately but leaves key calling details to inference.

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 7 parameters, so the description carries the full burden, but it addresses only the confirmation and revision guard. Critical parameters like replaceAll (which directly qualifies the 'one bounded' phrasing), idempotencyKey, and transcriptionId semantics are entirely undocumented. An agent could easily misread 'bounded' as always-single-occurrence and overlook replaceAll.

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 gives a specific verb and resource: 'bounded literal find-and-replace edit' on a 'tenant-owned transcript'. This clearly distinguishes it from sibling tools like rename_transcript (metadata rename) and repurpose_transcript. It stops short of naming those siblings explicitly, so it is a 4 rather than a 5.

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?

'Requires confirmation and an exact revision guard' states the prerequisites for calling but says nothing about when to choose this over rename_transcript or repurpose_transcript. Usage is implied by the description of what the tool does, but there are no explicit exclusions or alternative routing. A solid 3.

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