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

Annotations only supply readOnlyHint=false and destructiveHint=false. The description adds meaningful behavior beyond that: the entry is appended (not overwritten), it is durable, and it is surfaced to all future agents and humans via a rolling log. It omits any permission or scoping requirements for writing to a client log.

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?

Front-loaded with the action and its persistence semantics, then the exclusion, then the reference URL. Mostly efficient, though the rhetorical line 'If you don't record it, nobody else will know' is persuasion rather than specification and does not earn its place.

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?

With no output schema, the description does not need to explain return values, and an append-only note tool has little hidden behavior to disclose. The remaining gap is the client-versus-project routing against log_project_decision and the dual client/client_id parameters, which are left for the agent to infer.

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 67% with 6 parameters. The description's enumeration of decision/learning/preference/constraint meaningfully maps onto the kind enum values, but it says nothing about client vs client_id (both present), task_id linkage, or the summary/detail split. Baseline 3 fits given the schema carries most of the load.

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?

Specific verb (append) plus resource (client's rolling decisions log) with the scope qualifier 'durable' and 'client's'. It also names the sibling add_progress_note and the condition that selects it, so an agent can separate this from progress notes without opening either schema.

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?

Explicitly lists the four intended content types (decisions, learnings, preferences, constraints) and gives an exclusion with a redirect to add_progress_note. However it does not disambiguate from the client-vs-project boundary against sibling log_project_decision, leaving a plausible routing ambiguity unaddressed.

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