log_run

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

With no annotations, the description carries the full burden and does disclose genuine behavioral context: the record is persistent across sessions, the tool returns the registry id, and metrics/paths tolerate JSON strings or plain text. It does not say whether a run_id collision overwrites or duplicates an entry, what status values are meaningful, or what authorization is needed for a write.

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?

Four short clauses, front-loaded with the core action and persistence scope, then parameter hints, then the return value. Every sentence carries information, though the format note about JSON strings could be folded more tightly.

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 the description need not explain return values (mentioning the registry id is a minor redundancy). For a zero-annotation write tool, the main remaining gap is idempotency/uniqueness behavior around run_id and the meaning of status, which an agent would need before logging reliably. Overall it is close to complete for its complexity.

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, and it partially does: it explains 'kind' with concrete examples and clarifies the accepted format for 'metrics' and 'paths'. The remaining parameters (notes, run_id, status) receive no explanation at all, including the default 'logged' status and the identity semantics of run_id.

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 ('Record a run/event in the persistent project registry') with the cross-session memory intent in parentheses, so an agent knows this writes structured run history. It does not name or differentiate against obvious siblings like list_runs, run_details, or compare_runs, which are the read-side counterparts.

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 only implied by 'persistent project registry (cross-session memory)' and the kind examples such as 'md_report', 'prep', 'hypothesis'. There is no explicit statement of when to call this versus md_run_report or list_runs, and no prerequisites or exclusions are given.

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