editor_read

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuinely non-obvious behavioral context: the read targets the live buffer state including unsaved bytes and will not silently fall back to disk. It does not disclose error behavior for a missing buffer_id or an out-of-range offset/length, so it is not fully transparent.

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?

A single compact sentence with the highest-value constraint front-loaded. No filler, no restatement of the tool name, and the qualifier clause earns its place.

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?

With no output schema and 0% parameter coverage, the description carries the full burden and leaves major gaps: return format (raw bytes vs encoded string), units for offset/length, behavior when the range exceeds the buffer, and any auth or locking requirements for reading a live buffer.

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?

All three required parameters have 0% schema description coverage and the description says nothing about them. Critically, it never clarifies whether offset and length are byte-based or character-based, which is exactly the ambiguity an agent needs resolved before calling a buffer read.

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 (read) and a precisely scoped resource (the intended live in-memory buffer), plus a key qualifier ('including unsaved bytes; no disk fallback') that separates it from disk-oriented siblings like binary_read. It stops short of naming the sibling it competes with, so the differentiation is inferable rather than explicit.

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?

'No disk fallback' implies when this tool is appropriate (you want the editor's in-memory state rather than persisted bytes), but there is no explicit when-to-use guidance, no named alternative, and no stated precondition that buffer_id must come from editor_status or editor_context.

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