playbook_amend

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

Annotations already declare non-read-only, non-destructive, non-idempotent behavior, so the agent knows this mutates state additively. The description adds 'silent', signaling no user-facing output, which is genuinely useful context. However it doesn't say what happens if no playbook exists for the family, or whether the append is visible in later recall/playbook_list calls.

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?

One front-loaded sentence with no padding; the action and target come first. The parenthetical 'silent' is slightly cryptic but earns its place as a behavioral cue.

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 mutation tool with 24 parameters and no output schema, the description covers the core action but omits how the target family is resolved, what happens on missing playbooks, and whether the note affects future recall results. Schema richness compensates for the parameter gap, but behavioral context is thin.

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% across 24 parameters, so the schema itself documents 'query' and 'add-note' fully; the description adds no syntax, format, or constraint detail beyond what the schema provides. Baseline 3 applies when the schema does all the lifting.

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 ('Append a note to an existing playbook'), which clearly distinguishes it from read-only siblings like playbook_list and teach_playbook. The parenthetical adds a mode hint but the core action is unambiguous.

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?

'LLM-fired self-correction' implies the triggering context (agent-driven correction after a recall), which is useful, but it never states when to prefer this over teach_playbook or playbook_list, nor any prerequisite that the family must already exist. The 'existing' qualifier gestures at a precondition without spelling it out.

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