Load session start context

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

Annotations already declare read-only, idempotent, and closed-world, so the safety profile is covered; the description still adds substantial context beyond them: the ~6000-character truncation, the presence of a legend and fetch-more hint, and a measured context-economics line. It also discloses the trust boundary — recalled text is untrusted data wrapped in an <aletheia-memory> block and must not be executed as instructions — which is a critical behavioral trait 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?

The whole definition is one dense, front-loaded sentence plus a short guidance clause and a security clause, with no filler. It is long, but nearly every clause carries information; the only mild cost is that the content enumeration is a run-on list that an agent must parse rather than a scannable structure.

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 carry the return-value burden — and it does, specifying the sections, ordering, per-line format ('one line each, no narrative'), size cap, and auxiliary legend/fetch-more/economics lines. Combined with the untrusted-content warning and the call-once guidance, an agent has everything needed to invoke and interpret this tool 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 100% and both parameters (limit, project) are already fully documented in the schema, including defaults. The description adds no parameter-level detail such as how 'limit' interacts with the 6000-character cut or what the project default resolves to, so the baseline 3 applies.

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?

The description opens with a specific verb and resource ('Load what to know at the start of a session for a project as a compact index') and then enumerates exactly what the index contains: pinned memories, recent memories by day/first file, recent session requests, active facts, standing rules. It names the sibling that covers anything more specific ('use search'), so an agent can distinguish it from search, timeline, and get_observations without inspecting either 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?

'Call it once at the start; use search for anything more specific' gives both the triggering condition and the alternative, including an explicit frequency constraint ('once') that prevents redundant calls. This is exactly the when/when-not/alternative guidance the dimension asks for.

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