mh_search

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

With no annotations, the description carries the behavioral burden and does it well: it discloses hybrid retrieval (vector semantics + metadata filtering) and a non-obvious default exclusion (nssm service ledger not returned unless source is specified). It stops short of explicitly declaring read-only behavior, but 'search/retrieve' plus the absence of side-effect language makes that reasonably clear.

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?

Three dense sentences with no filler: the core purpose is front-loaded, and each subsequent sentence delivers either routing guidance or an important retrieval caveat. The warning about standard questions is placed immediately after the purpose, which is exactly where an agent needs it.

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 an 8-parameter search tool with no output schema, the description covers the essential context: what is returned, when to use it, how the retrieval works, which metadata filters apply, and an important default-exclusion gotcha. An agent has enough to decide whether to call this tool and how to route alternative requests.

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 38%, so the description must compensate. It does so by identifying layer, category, source, tags, and time as metadata filters and giving a concrete example for source. It does not explain layer's k/m enum or top_k semantics, but the added context goes meaningfully beyond the sparse schema.

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 clear verb and resource: retrieve the boss's unified memory and return raw entries, specifically suited for historical details, concrete events, and full accounts of past pitfalls. It further distinguishes itself from curated answer tools like mh_tool and mh_tools_list, so an agent can tell them apart.

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 describes when to use the tool (historical details, specific events, full stories of pitfalls) and when not to (standard questions about the boss, preferences, environment, services, ports, project changes), routing those to mh_tools_list → mh_tool. It also gives a concrete alternative path for nssm service ledger queries by specifying source='agent-matrix'.

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