memory_verify

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

With no annotations, the description carries full burden and does well: it discloses return shapes, the {success:false,error:'not found'} failure mode, session:null handling, and explicitly states it does NOT change confidence or access counts and checks citation records rather than factual truth. It stops short of naming required auth/permissions, keeping it just below a 5.

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 purpose, then return shapes, then error clauses, then the explicit non-guarantee and the sibling pointer. Dense but every sentence carries distinct information; slightly long but no wasted filler.

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?

There is no output schema, so the description must explain returns, which it does in full detail for both memory and observation cases plus errors; combined with the two-param required schema and clear semantics, nothing an agent needs to call it correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning: it clarifies that 'project' must be an exact registered identifier and constrains the '*' wildcard to deliberate cross-project use, and that missing id/project returns an error.

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 precise verb and resource: 'Read stored provenance for one memory or observation ID in an explicit project.' It clearly scopes the operation to a single ID and distinguishes itself from content-reading siblings by returning provenance/citation metadata rather than source text.

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 to use '*' only for deliberate cross-project verification, and routes the agent to memory_smart_search expandIds or memory_timeline when it actually wants source content. This is a rare, complete when/when-not/alternative triage.

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