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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real context the annotations do not: newest-first ordering, that results come back as two independently paged groups, the permission requirement ('needs project Read'), and the picker it mirrors. The only omitted traits are page-size limits and empty-result behavior.

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?

Four sentences, no filler, front-loaded with the core result description and then the matching rules and the ingestionId narrowing. It is dense and heavily compressed, but every sentence carries distinct information; the two-group semantics could have been slightly clearer without adding length.

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?

This is a read tool with no output schema, so the description must carry the return-shape burden, and it does reasonably well: it discloses the two paged groups, ordering, the two per-group cursors (matching afterSources/afterMemories), and that ids are the follow-on handle. Only the page-size cap and default are left to the schema, which already states them.

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 and the schema already documents each parameter. The description nonetheless adds semantics beyond the schema by explaining what the search term actually matches against for each group and how ingestionId narrows both groups simultaneously. It does not, however, clarify cursor pairing behavior across the two groups beyond what the schema field names imply.

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 concrete verb-resource: returns 'memories and sources matching a search' in two paged groups, and specifies what actually matches (source text/data point id, memory words/artifact id). It also differentiates itself downstream by naming get_lineage and get_timeline as consumers of each entry's id. It does not, however, distinguish itself from near-siblings like recall_memory or explain_ingestion, which also surface memory content.

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 one conditional usage note ('Pass ingestionId to list the sources one ingestion carried and the memories drawn from them') and a chaining hint ('Each entry's id is what get_lineage and get_timeline take'), both useful. But no guidance is given on when this tool is the right choice versus recall_memory, explain_ingestion, or list_requests, so usage is mostly implied rather than stated.

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