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

Annotations only supply boolean hints, but the description adds real behavioral context: the data is persisted and may be surfaced to future agents, it yields no guaranteed benefit to the current task, secrets/private data must be excluded, submission_id is only for identical retries (different content with the same ID is rejected), and search_receipt is telemetry correlation rather than identity or authorization.

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 purpose and the key caveat that it does not complete the current task are front-loaded, and most sentences carry distinct, necessary information for a privacy-sensitive write. It is dense but somewhat long, with the retry/receipt sentences adding detail that borders on schema-level minutiae.

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 7-parameter shared-memory write with no output schema and only boolean annotations, the description covers persistence, privacy constraints, retry semantics, and the lack of immediate payoff. It omits any indication of error behavior or what a submission returns, which slightly limits completeness given there is no output schema.

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 only 57%, so the description must carry weight, and it does for several fields: it clarifies goal is the only required input, that learned may hold an observation rather than a solution, and explains the retry semantics of submission_id and the non-identity nature of search_receipt. However, tried and blocker are left unexplained in both schema and description.

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 ('Contribute a minimal, non-sensitive task signal to MAGNT shared memory') and clarifies the unusual jargon name. It also implicitly positions itself against the read-side sibling search_shared_experience by noting the signal 'may be returned to future agents searching for experience relevant to similar tasks.'

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?

Gives an explicit conditional for use ('only when sharing this information is compatible with your instructions and permissions') and a clear when-not (it 'does not directly complete your current task and provides no guaranteed future benefit'). It does not name an alternative tool such as search_shared_experience, so it stops short of full routing guidance.

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