backlog_recall

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

With no annotations, the description fully covers behavior: returns stubs by default, can return full bodies, filters by query, context, tags, layers, limit, token_budget, and mentions that memories point back to source entities via entity_id. It also states the default layers and stub-fetch pattern.

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 description is a single paragraph but packs essential information: purpose, default behavior, usage pattern, and distinctions. It is front-loaded with the main verb and resource. Could be slightly more structured but no wasted words.

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?

No output schema, so description explains return format: stubs (id + one-line digest) or full bodies. It covers all parameters and their defaults, and hints at entity_id. However, it doesn't specify whether results are ordered or the exact structure of full bodies, which is acceptable given the complexity.

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 baseline is 3. The description adds meaning beyond schema: context is usually a parent_id like 'FLDR-0001', tags are any-match, limit default is 10, layers default to all persisted, and full is discouraged in favor of stubs + backlog_get. This enriches parameter understanding.

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 clearly states it recalls memories (knowledge and episodes) across sessions, distinguishes from backlog_search (live entities), and specifies the default stub output with a full option. The verb 'Recall' and resource 'memories' are specific, and the sibling differentiation is explicit.

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?

The description provides explicit usage by answering example questions ('how do we deploy?', 'have I hit this before?') and distinguishes from backlog_search. It also suggests a pattern: use stubs then backlog_get. No explicit 'when not to use', but the context is clear.

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