Record a failed approach immediately when an attempt doesn't work, including what was tried and why it failed so other agents can avoid repeating the same mistake.
Record a failed approach IMMEDIATELY when something doesn't work.
| Name | Required | Description | Default |
|---|---|---|---|
| approach | Yes | What was attempted | |
| why_failed | Yes | Why it failed |
Changes observed during successful MCP inspections.
v3.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations only declare readOnlyHint=false, so the description carries most of the behavioral burden. "Record ... IMMEDIATELY" is consistent with a write operation and adds timing urgency, but nothing is said about persistence scope, deduplication of repeated failures, or whether entries are later surfaced via get_patterns / search_context.
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 front-loaded sentence with zero waste; the trigger condition is stated before any qualifier. The all-caps "IMMEDIATELY" is functional emphasis rather than filler, though the sentence is so short it leaves no room for the routing detail an agent needs.
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 simple two-parameter write tool with full schema coverage and no output schema, the description is minimally sufficient to call correctly. It is incomplete regarding how a recorded failure relates to the rest of the context/pattern toolset, which matters given fourteen siblings.
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% with both required parameters (approach, why_failed) fully documented in the schema. The description adds no additional meaning about granularity, what counts as an "approach," or how specific why_failed should be, so baseline 3 applies.
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?
"Record a failed approach" states a specific verb and resource, and the tool is easily distinguished from siblings like save_context or record_success at the verb level. It does not, however, explicitly contrast itself with record_success, the closest sibling.
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?
"IMMEDIATELY when something doesn't work" gives a clear trigger condition and timing emphasis, which is more than nothing. But it names no alternative, no exclusions, and no prerequisites (e.g. when to prefer save_summary or record_success instead), so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.