Diffusion Love Knowledge

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety behavior is covered. The description adds one useful fact beyond them — that results come from a 'pinned' snapshot rather than live data — but says nothing about ordering, pagination, or what a 'dated feed event' contains.

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?

A single tight sentence with no filler; the scope ('one project family') is front-loaded before the data source.

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, zero param descriptions, and three parameters, one sentence is too thin. An agent cannot learn the accepted format of 'since', the meaning of 'limit', or what an event looks like without trial and error.

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 carries the full param burden. 'one project family' and 'dated' loosely imply family_slug and since, but neither is named explicitly, and the limit parameter (1–50) is never mentioned in the description or schema, leaving a hard cap an agent could trip over.

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') and resource ('dated feed events') scoped to 'one project family', which maps to the required family_slug. It is distinguishable from read_knowledge in that it returns feed events rather than knowledge entries, though the phrase 'pinned news snapshot' is unexplained jargon that muddies the exact data source.

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 no guidance on when to use this tool versus the siblings (read_knowledge, search_knowledge, tooling_for). The description never states a triggering condition or an exclusion, leaving routing entirely to inference.

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?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real context beyond that: the data comes from a 'pinned knowledge snapshot' and returns available anchors. It still says nothing about what happens when a page or section does not exist.

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?

A single front-loaded sentence with no filler; the core verb+resource comes first. The trailing 'including available anchors' clause is slightly vague about whether anchors are returned or accepted, which keeps it short of a 5.

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 two-parameter read tool with no output schema, the description establishes the source and payload nature, which is adequate. It omits identifier syntax, the meaning of 'anchors', and error behavior on a missing page, leaving meaningful gaps for an agent invoking it correctly on the first try.

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 carries the burden, and it does map loosely onto both parameters by naming 'page' and 'section'. However, it never explains the expected identifier format (path, slug, anchor) or that page is required while section is optional, so the gap is only partially closed.

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 states a specific verb (Read) and a specific resource (an exact indexed Markdown page or section from the pinned knowledge snapshot), plus that anchors are included. It hints at the boundary with search_knowledge via 'exact' but never names the sibling, so differentiation is left partly to inference.

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?

Usage is only implied: 'exact' page/section suggests the caller must already know the identifier and should use search_knowledge to discover it first, but no when-to-use, when-not-to-use, or named alternative is given. An agent can infer the workflow but is not told it.

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?

Annotations already declare read-only, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. The description adds genuine context beyond that: the search is lexical rather than semantic, it operates on a pinned public snapshot, and hits are unapproved matches rather than vetted proposals.

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 short, front-loaded sentences with no filler; the core action comes first and the caveat about result semantics follows. Nothing is redundant with the title or schema.

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 four-parameter search tool with no output schema and no schema descriptions, the description should clarify parameter meaning and how it differs from read_knowledge. It does address result semantics, which is valuable, but leaves the parameter surface entirely unexplained.

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% across four parameters (query, limit, domain, project), so the description carries the full documentation burden and supplies none of it. It never explains what 'domain' or 'project' scope to, what 'limit' defaults to, or the expected query format.

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 ('lexically search') and resource ('pinned public knowledge snapshot'), which clearly distinguishes it from a semantic or proposal search. It does not, however, say how it relates to the sibling read_knowledge, so the differentiation is incomplete.

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 no explicit when-to-use guidance or comparison with alternatives such as read_knowledge or project_updates. The closing clause ('Results are search matches, not approved proposals') hints at a usage caution, but it does not tell the agent when this tool is the right pick.

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?

Annotations already declare readOnlyHint, idempotentHint, closed-world, and non-destructive, so the safety profile is covered. The description does add one genuinely useful behavioral fact — results are incomplete because tool relationships are still being built — which tells an agent not to treat an empty/short result as definitive. It says nothing about result shape or matching semantics.

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 short sentences with no padding, and the coverage caveat is front-loaded after the purpose. It is efficient, though the first sentence's wording is what creates the purpose ambiguity.

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 one-parameter, annotation-covered, read-only lookup with no output schema, the description covers the main risk (partial coverage) but omits the parameter format and what 'snapshot evidence' actually contains. Adequate but with clear gaps given the 0% schema coverage.

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% for the single required parameter 'base_model', so the description must compensate and does not. It never specifies the expected identifier form (e.g., a canonical model slug or registry ID) or whether matching is exact or fuzzy, leaving the agent to guess what string to pass.

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 verb 'find' is clear, but the resource is inconsistent: the title promises 'tooling' while the description says 'snapshot evidence associated with a base model.' An agent cannot tell whether it is retrieving tools, snapshots, or evidence, and no sibling differentiation is offered against project_updates/read_knowledge/search_knowledge.

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 no statement of when to reach for this tool versus the sibling knowledge-search tools, nor any prerequisites. The only guidance-adjacent content is the caveat that coverage is partial, which is a warning rather than a selection rule.

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