Record to the ledger

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

No annotations are provided, so the description must carry the full burden. It does: it discloses persistence ('Nothing here is ever deleted'), the replacement behavior ('the old entry stays on disk, marked replaced'), and the rationale for text formatting to support future recall. These are non-obvious behaviors an agent needs to know.

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?

The description is longer than typical but every sentence serves a purpose: it front-loads the core action, then provides the when-list, then per-field semantics and lifecycle rules. It is structured as a compact reference, not padded prose. Slight verbosity is justified by the tool's complexity.

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 6-parameter tool with two enums and no output schema, the description covers all necessary aspects: when to invoke, what each field means, required ref conditions, text formatting rules, supersede semantics, and the permanence guarantee. It also implicitly contrasts with recall. Nothing an agent needs to call correctly 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 coverage is 100%, so every parameter already has a description. The description adds value beyond that by explaining the semantic role of each field in context: e.g., 'ref' is required for specific kinds, 'text' should lead with WHAT for recallability, 'refresh' indicates reproducibility, and 'supersedes' links to an earlier entry. This enriches the schema without redundancy.

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?

The description opens with a clear verb-resource pair ('Append one fact to this project's ledger') and specifies the exact timing ('at the moment it is produced'). It distinguishes itself from the sibling tool recall by framing this as the write operation ('recall scores entries against a future task'), so an agent can tell them apart without inspecting schemas.

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?

The description enumerates specific trigger conditions ('Call it right after: the user states a rule or a boundary... the user corrects something... you choose between alternatives...') and gives explicit formatting guidance ('say what it is, then why') plus rules for required refs per kind. It also explains when to use supersedes to retire an entry. This is explicit and actionable.

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