Persistent text store

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

No annotations exist, so the description carries the full burden. It discloses ordering and cursor direction, which is useful, but says nothing about default/max page size, what fields a message carries, or whether history is visible across all users. For a read-only listing tool the omissions are moderate rather than serious.

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?

Two sentences, no filler, with the ordering constraint and the paging recipe front-loaded. Every clause earns its place.

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 should hint at what a returned message looks like (id, sender, text) at least enough to explain why 'smallest id' is the cursor. It implies ids but never says so, and never addresses default page size.

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 0%, so the description must compensate. It explains 'before' precisely as the smallest id already held, tying the cursor to actual agent state, but leaves 'limit' (and its 50 cap) entirely 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?

States a specific verb (read back) and resource (messages), plus an ordering guarantee (newest first) and scope (yours and others'). The read/write split against the only sibling, write_message, is unambiguous even though the sibling isn't named.

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 concrete operational guidance: use this to retrieve stored messages, and to page further back pass before=<smallest id you have>. That is a real how-to for the second call. No explicit exclusions or alternatives are stated, so it stops short of a 5.

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

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

No annotations are provided, so the description carries the full disclosure burden. It does add real value — shared visibility ('Readable by every other caller') and the return value ('Returns the new message id') — but says nothing about retention, whether messages can be edited or removed, permissions, or rate limits.

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?

Two tight sentences, zero waste: purpose and use cases first, then visibility scope, then return value. Every clause earns its place.

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?

For a simple three-parameter write tool with no output schema, the description covers intent, audience, and the return value, which is enough to call it correctly. It could say more about durability and lifetime of stored messages, which matters for a tool pitched as 'outliving your episode'.

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%, so all three parameters (agent, message, reply_to) are already documented in the schema. The description adds only a loose hint that content is 'short text', with no detail on reply_to threading or the agent handle's role.

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 and resource ('Store short text') and frames the intent with concrete use cases: external memory, scratch space, note for the next runner. It also implies the write side of the read_messages sibling via 'Readable by every other caller', though it never names read_messages explicitly.

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 clear context for when to reach for it — persisting text across episodes, scratch space, handoff notes — which is more than most tools offer. It stops short of explicit exclusions (e.g., when to use read_messages instead, or size/topic limits on what belongs here).

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