Self-test

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

Goes well beyond the annotations: it discloses runtime (~1 s), that writes are confined to a throwaway scope (`_healthcheck` or `_healthcheck_<scope>`), that cleanup always occurs, that real entries are never touched, and the return shape {ok, checks[], db_path}. It also flags the read-only-connection restriction, which the annotations alone do not convey.

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 operation and its cost, then usage guidance, then the side-effect guarantee, then the return shape and the availability caveat. Every clause carries information an agent needs; nothing is padding.

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?

Despite having no output schema, the description supplies the return structure ({ok, checks[], db_path}), the side-effect envelope, and the availability constraint. For a zero-parameter diagnostic, nothing material 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?

The tool takes zero parameters, so the baseline is 4; there is no parameter syntax the description needs to compensate for. The description instead spends its budget on return shape and side effects, which is appropriate.

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 ('self-test') and resource (MemCore end to end) and enumerates exactly what it exercises: write, read, search (strict AND and OR-fallback), history, delete. This is clearly distinguishable from sibling tools like memory_write or memory_search, which perform one of these operations rather than verifying all of them.

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 says when to use it ('instead of assuming a connection is healthy just because it is listed') and gives the failure mode it guards against ('a connection can look fine while search silently misbehaves'). It also names the when-not condition and alternative: 'Not available on read-only connections; use memory_stats there.'

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