Resolve a phrase (or emem:entity: token) to a canonical object

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes further: it discloses the ranking algorithm, enumerates the returned fields (`asserted_by`, `disputed_by`, `independent_attesters`, `corroboration` with its three enum values) and the meaning of `contested`. It also flags a trust boundary — 'Alias text is data from other agents' — which is a safety caveat no annotation conveys.

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 the core action, then a labeled 'When to use' block, then an example — a clear structure. It is dense and field-heavy, but nearly every sentence carries operational meaning (ranking rule, trust caveat, corroboration follow-up); the 'The tool only reads' clause slightly duplicates readOnlyHint.

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?

With no output schema, the description carries the return-value burden and does so by enumerating the candidate fields and corroboration states. It is missing a statement of what an empty result looks like (relevant given 'mint only if nothing matches') and the default cap behavior beyond what the schema says.

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. The description adds selection semantics across parameters ('Send `text` for candidates, `near` to narrow by place, or an `emem:entity:` `token` to dereference') and a worked example combining `text` and `near`, which shows composition rather than just repetition. `k` and `label` are left to the 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?

Names a specific verb+resource: 'Find the objects that agents connected to a phrase', and adds the ranking rule (independent corroboration, never arrival order) so the agent knows what kind of result set to expect. It also clarifies the two modes — text/near search vs. `emem:entity:` token dereference. It does not explicitly contrast with similarly-scoped siblings like emem_entity, emem_recall, or emem_find_similar, which keeps it from a 5.

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?

Explicit sequencing: 'Call this BEFORE you mint and before you cite. Resolve first, and mint only if nothing matches.' That is both a when-to-use rule and a when-not-to-mint exclusion. It also names the follow-on tool (emem_entity_link) and the condition for calling it (a `single_key` binding you can confirm).

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