canon

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

With no annotations, the description carries the full burden; it does disclose useful behavior — the authority ordering ("outranks notes and docs"), the 7-day window on changes, and that conflicts are counted rather than resolved. It never states that the call is read-only, nor anything about response size, truncation, or what an empty call returns, so key behavioral facts for an aggregation tool are left to inference.

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 payload contents are front-loaded, followed by parameter formats, then usage guidance — a sensible order with no filler sentences. The parenthetical-heavy phrasing ("(precedence, owner-only facts, rules)", "(product:<key>)") is dense but every clause conveys scope the agent would otherwise have to guess.

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 parameterless-by-default read aggregator with no annotations and no output schema, the description covers what makes up the answer (core, product facts, work state, vendors, recent changes, conflict count) and when to fetch it. The only unstated items — default behavior with no arguments and payload size — are minor relative to what is disclosed.

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%, and the description compensates well by defining both parameters: product is a key like "santa", and repo is a git remote URL or "owner/name" matched against work:<key>.repos. It does not say how the two interact or what happens when both or neither are supplied, which is the remaining gap.

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 names a concrete resource and enumerates its contents (company core, product customer facts, work state, vendors, 7-day change log, open conflict count), which is far more than a restatement of the name 'canon'. The verb is implicit ("Read it") rather than stated up front, and no sibling such as fact_get, changes, or search is named as a contrast, so the 5 is withheld.

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?

It gives explicit timing guidance: read before work on a product and after a compaction, and asserts precedence over notes and docs. It lacks any when-not or named-alternative routing (e.g. when to prefer fact_get or changes instead), which keeps it at 4 rather than 5.

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