amem_graph

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

No annotations exist, so the description carries the full burden. 'Dump stored facts' strongly implies a read-only operation and the scoping to a workspace or git repo is useful, but it says nothing about result size, truncation, ordering, or what happens when workspace is omitted (it is optional).

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?

Three short sentences with no filler: capability first, usage trigger second, sibling routing third. Front-loaded and every clause carries information.

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 two optional params and no output schema, the description adequately covers what the tool does and what categories of data come back. It falls short only on behavioral detail an agent might want (default workspace behavior, response volume), which is minor for a read-only dump.

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 50%: 'days' is documented in the schema but 'workspace' is bare. The description compensates by stating that the workspace may be a git repo, clarifying the accepted value domain of the undocumented parameter, though it never mentions the lookback/window at all.

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 ('Dump') plus the resource ('stored facts for a workspace or git repo') and enumerates what is returned: claims, components, flows, recent activity. It also names the sibling it is not (amem_context), so an agent can distinguish it without opening a 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?

Gives an explicit trigger ('Use when asked what amem remembers about a project') and an explicit alternative with the condition that selects it ('Prefer amem_context for a ranked packet for the current question'). Both the when and the when-not are present.

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