session_search

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

With no annotations, the description carries the behavioral burden. It discloses that searches are 'governed' (implying access control) and mentions FTS5, but 'governed' is ambiguous. It does not state whether the tool is read-only, what happens with no args (browse recent is stated), or any rate limits or side effects. Since the description adds some context but lacks precision, a 3 is appropriate.

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 description is three sentences, front-loaded with the core purpose, and uses a clear colon-separated structure for modes. Every sentence adds value with no redundant content.

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 tool with four modes and no output schema, the description covers the main usage patterns well. It doesn't explain return format or edge cases, but it provides enough for an agent to select and invoke the tool correctly for the primary tasks. The schema fills in some remaining parameter details.

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?

Despite only 57% schema coverage, the description adds significant meaning by mapping parameter combinations to use cases (query for discovery, session_id for whole session, session_id+around_message_id for scrolling, no args for browse). This goes beyond schema bare descriptions, though it leaves sort and role_filter unaddressed, which the schema partially documents.

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 clearly states it searches and recalls past Hermes conversations, and distinguishes from siblings like grep and search_compliance_docs by explicitly scoping to conversations. The multiple usage modes (discovery, read session, scroll, browse) further clarify the tool's purpose.

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?

Provides concrete usage scenarios with argument combinations (query for discovery, session_id for reading, etc.), which implies when to use each. However, it does not explicitly name alternatives or state when not to use this tool, so it stops short of full exclusion guidance.

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