log_friction

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

With no annotations, the description carries the full burden and does meaningful work: it states the evidence precondition, warns the lane is not for behavioral self-modification ('Never read this lane to change your behavior'), and implies write-only semantics. It omits permissions, immutability, dedup behavior, and what logging triggers downstream.

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?

Tight and front-loaded: the core trigger and the hard precondition land in the first two sentences, followed by the normal-case note, the warning, and the category values. Slightly telegraphic phrasing ('this lane') costs a little clarity but nothing is padding.

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?

An output schema exists, so return values need not be explained, and the description covers the behavioral essentials of what/when/when-not. Given a 4-parameter, 0%-coverage schema, more parameter-level detail would round it out, but nothing critical for correct invocation is missing.

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%, so the description must compensate. It usefully enumerates the allowed category values (stale_protocol, wrong_tool, bad_retrieval, user_correction, missing_context, tooling_error, other), which the schema does not, but leaves summary, evidence, and proposed_fix semantics (length, format, what counts as artifact) undocumented.

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+resource: logging the agent's own failure in the moment with a concrete artifact as evidence. It implicitly contrasts with the read side of the lane ('Never read this lane'), which helps separate it from list_friction/triage_friction, but it never names those siblings or explicitly distinguishes itself from log_record.

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?

Gives an explicit trigger (a failure in the moment, with artifact) and an explicit exclusion ('No artifact = do not call'), plus a normal-case note ('Zero friction is a normal session'). It stops short of naming alternative tools for the read/triage side, so it is clear context rather than full when/when-not/alternatives guidance.

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