editor_events

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

With readOnlyHint already covering safety, the description adds substantial non-structured behavior: a 4096-event rolling buffer held across script reloads, Truncated=true when events after sinceSeq were overwritten, and HostStartedUtc signaling an editor restart that reset the sequence. It also clarifies that 'log' covers managed lines only, with native engine lines (compiler output) remaining in the log file.

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?

Front-loaded with purpose and ordering in the first clause, then operational caveats. The long kind list is dense but load-bearing since no enum exists; no sentence is filler, though the block is heavier than ideal for a single stream read.

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-shape explanation is unnecessary; the description still volunteers the two semantically important output fields (Truncated, HostStartedUtc) that govern correct pagination and reset handling. Retention limits, ordering, and kind scope are all covered for a 4-param, zero-required read tool.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning the schema lacks: it enumerates the valid kind strings even though the schema's `kinds` items have no enum, and it defines the sequence space (reset on host start, gap detection via Truncated). `limit` and `waitSeconds` are left entirely to the schema.

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 ("Returns the editor's recorded events"), plus ordering ("oldest first") and a cursor ("after a sequence number"), which pins down exactly what this stream is. The enumerated Kinds make it trivially distinguishable from siblings like logs_tail or editor_wait_for.

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?

Usage is implied rather than stated: the retention/truncation and HostStartedUtc notes imply polling and restart-recovery patterns, and the 'log' kind note implies 'use this rather than logs_tail for engine output.' But no sentence explicitly says when to pick this over logs_tail, logs_errors, or editor_wait_for, and there are no exclusions.

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