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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuine behavioral context beyond that: results are compacted snippets, beliefs are filtered to 'active, contradiction-free', and skills are 'verified' — telling the agent the result set is pre-filtered rather than raw. It stops short of describing ranking, token budgeting, or what reinforce_ids actually changes.

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?

Two sentences with no filler; the return inventory comes first and the routing instruction second. Every clause carries information the agent needs, and the alternative is placed where it will be read before invocation.

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 read tool with no output schema, the description usefully covers what comes back and how compact it is, which is the main thing the schema cannot express. The gap is that it never explains result ordering or the effect of reinforcing prior IDs, both of which matter for a memory-retrieval loop.

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 description coverage is 100%, so every parameter is already documented at the field level and the baseline applies. The description only adds the implicit detail that matching is hybrid keyword-plus-meaning, and says nothing about scope, k_beliefs/k_episodes, full_episodes, or reinforce_ids beyond what the schema states.

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 ('Search persistent memory by keyword and meaning') and enumerates the four distinct return categories: episodic snippets, active contradiction-free beliefs, root-cause chains, and verified Python skills. That enumeration lets an agent distinguish it from siblings like oxyo_belief_revisions or oxyo_causal_infer without opening any 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 sets the usage condition ('targeted mid-session lookups') and names the alternative for a different condition ('call oxyo_session_pack instead at session cold start'). Strong when/when-not pairing, though it offers no guidance relative to the other retrieval-adjacent siblings such as oxyo_belief_revisions.

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