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

With no annotations, the description carries the full behavioral burden and does well: it discloses deduplication ('Identical content is stored once, so retries are safe') and billing/idempotency semantics for idempotency_key. It does not mention permissions or what superseding does to the older record beyond marking it replaced, leaving a small gap.

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?

It is a dense but well-front-loaded paragraph: the core action leads, then each parameter's semantic role follows in a logical order. Every sentence adds information, though the block format rather than a list makes it slightly harder to scan for a 9-parameter tool.

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 return values need not be explained, and the description focuses correctly on input semantics and side effects. For a 9-parameter mutation tool with zero schema coverage, it covers most of what an agent needs, missing only project/tags semantics and any note on required-field behavior.

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 largely does: kind enumerants with meanings, title as one line, body for details/reasons/errors, files as related paths, supersedes as replacement marking, and idempotency_key semantics. It leaves project, tags, and the exact status values per kind only partially explained (project and tags unexplained), so not a full 5.

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 specific verb+resource: 'Store one fact about the project.' It clearly distinguishes the semantic content being stored (facts with kinds) rather than just restating the name 'remember.' It does not explicitly contrast with siblings like recall or update, but the purpose 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?

The kind taxonomy (decision/attempt/task/note) implicitly guides what to store, and status values per kind are given. However, there is no explicit when-to-use-this-vs-recall-or-update guidance, and no stated preconditions (e.g., does the project need to exist first via project_open?). Usage is inferable but not framed as guidance.

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