memory_recall

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

With no annotations provided, the description carries the full burden, and it offers exactly one behavioral trait: the embedding model is 'loopback-only,' implying local/offline inference rather than an external API call — a genuinely useful privacy/architecture disclosure. It does not state whether the operation is read-only, how min_similarity affects result filtering, what happens on no match, or latency/failure characteristics. The single trait earns some credit but far short of the burden for an unannotated tool.

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?

A single front-loaded sentence with no filler — the verb 'Recall' leads immediately and every word contributes. The 'loopback-only embedding model' clause is compressed jargon that trades clarity for brevity, and the description is terse to the point of under-specification for a 6-parameter tool, so it is efficient but not perfectly calibrated.

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 tool with 6 parameters, 3 required, zero annotations, and 0% schema description coverage, a single sentence is not enough — the output schema covers return values, but parameter semantics and selection guidance are entirely absent. An agent would need sibling descriptions or trial-and-error to know how to populate agent_name, project_key, and min_similarity correctly.

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 0%, so the description must compensate by explaining the six parameters, but it names none of them. The phrase 'recall related project facts' only weakly implies that query is the lookup text and that results are scoped to project facts. agent_name, project_key, limit, model, and min_similarity remain semantically undefined in both the schema and the 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 ('Recall related project facts') plus the method ('loopback-only embedding model'), making the semantic-search read intent clear. The embedding detail distinguishes it from write-style siblings like queue_durable_fact, sync_offline_facts, and memory_consolidation. However, it does not fully differentiate from read-style siblings like pull_truth, get_sync_context, or list, which could also plausibly return project facts.

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?

There is no statement of when to use this tool versus any of the 15 siblings. Several siblings overlap in domain (memory_bootstrap, memory_consolidation, pull_truth, get_sync_context, list), and the description provides no selection criterion such as 'use for semantic similarity recall vs. enumerated listing' or 'do not use for writes.' An agent must infer the use case from the tool name alone.

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