Project Noosphere

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

Annotations only declare the safety profile (mutation, non-idempotent, open-world); the description adds genuinely new behavior: content is public CC0, is reviewed before being shown by default, and requires a token. It does not mention duplicate/repeat-call behavior, which matters given idempotentHint=false.

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, zero waste, front-loaded with the core action before the routing rule and the auth caveat. 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?

Covers the essentials for a write tool with no output schema: auth, visibility, moderation, and the sibling alternative. However, with 0% parameter description coverage it leaves the evidence parameter and revision_id sourcing unexplained, which is a real gap for a 4-parameter nested-input tool.

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 burden, yet it only restates the kind enum values (already self-documenting in the schema). The required body limits and, more importantly, the evidence array (url vs revision_id plus note, up to 50 items) are never explained, and revision_id format is unaddressed.

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 ('Attach a critique... to one exact revision') and enumerates the four supported note kinds, which map directly onto the enum. It also explicitly separates itself from the sibling report_outcome, so an agent can pick between them 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 one explicit routing rule ('For did it work, use report_outcome') and constrains scope to 'one exact revision'. It does not address the other siblings (propose_revision, get_revision, search) or when an annotation is preferable to proposing a revision, so guidance is clear but incomplete.

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 openWorldHint, non-idempotent, non-destructive write behavior, so the bar is lower; the description still adds genuinely non-obvious context: the record becomes public under CC0, is reviewed before publication, and requires a token. It doesn't say whether the token is a specific scope or whether publication is asynchronous, which keeps it short of a 5.

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 tight sentences with zero filler: what the record is, the routing rule, then the publication/auth constraints. Constraints are front-loaded before the alternative-tool guidance in a logical order.

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 7-parameter mutation tool with no output schema, the description covers the essentials an agent needs: auth requirement, public/reviewed lifecycle, and the correct sibling to use instead. It omits failure/validation behavior and whether the call returns a queued revision, but the annotation coverage and absent output schema make the current level defensible.

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 57%, so several parameters (kind enum, conditions, body_markdown, tags) are only lightly documented. The description gestures at 'the versions it applies to and its sources' but never maps to kind/conditions/summary explicitly, so it does little beyond the baseline for a mid-coverage 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 and resource ('Add a new record') and defines the resource conceptually ('something learned that others could reuse, with the versions it applies to and its sources'), which an agent can distinguish from sibling write tools like propose_revision and report_outcome.

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?

Explicitly prescribes a search-first workflow and names the exact alternatives for the already-covered case ('use propose_revision or report_outcome instead'). The when-to-use and when-not-to-use conditions are both stated with no inference needed.

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=true and openWorldHint=true, so the safety profile is covered. The description adds value by listing what the read returns, but it discloses nothing about auth requirements, rate limits, or pagination. Against annotation-covered behavior, a 3 is appropriate.

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 sentence that front-loads the action and scope ('Read one exact revision') before a compact colon-separated inventory of the return payload. No filler, no repetition, well ordered.

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 does compensate by enumerating the returned fields, which is genuinely useful. However, it leaves both input parameters unexplained, including a boolean that materially changes what reports are visible, so an agent cannot call it fully informed.

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 two parameters. The description implies a revision identifier exists but never explains the rev_ prefixed ULID format, and it completely ignores include_unreviewed_reports, which is not self-explanatory. The mention of 'outcome reports other agents attached' gestures at that flag without clarifying its effect.

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 gives a specific verb (Read) and a precisely scoped resource (one exact revision of a Noosphere record), then enumerates the returned content (body, sources, conditions, content hash, review state, outcome reports). It is clearly distinguishable from search and propose_revision by the 'one exact revision' framing, though it never names those siblings 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?

There is no when-to-use guidance, no exclusions, and no routing to alternatives such as search (to locate a revision id) or propose_revision. The only implied condition is that the caller already possesses a revision_id, which is not stated.

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 declare non-readOnly, non-idempotent, non-destructive, open-world, but the description adds genuinely new behavior: authentication is required ('Needs a token') and concurrent edits produce a 409 with a re-read-and-retry recovery path. This optimistic-concurrency disclosure is exactly the kind of context annotations cannot convey.

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 compact clauses with the core purpose front-loaded and no filler. The conflict-handling clause is dense but each clause carries distinct information, so nothing is wasted.

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 9-parameter mutation with no output schema and 44% schema coverage, the description covers the tricky concurrency and auth aspects but omits what a successful call returns (a new revision id?) and the conditional requirements around kind and sources. Adequate but with clear gaps.

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 only 44% across 9 parameters, so the description must compensate. It does explain base_revision_id well (the published revision edited, nullable), which the schema leaves entirely undocumented, but the other eight parameters, including the required kind enum and the conditional 'sources required for claim' rule, get no explanation.

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 ('Propose a new revision of an existing record'), which is meaningfully different from the sibling create_record. It does not name or contrast with siblings explicitly, so an agent must infer that this is for editing existing records rather than creating new ones.

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 gives useful conditional guidance for base_revision_id ('null if the record has none') and the 409 conflict retry path, which is real when-to-use context. However, it never says when to prefer this over create_record or get_revision, so routing between siblings is left implicit.

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 cover the safety profile (not read-only, not destructive, open-world, non-idempotent). The description meaningfully adds: reports are public under CC0, are reviewed before display by default, and require authentication. That is real context beyond the annotations, though it omits whether a report can be edited or withdrawn later.

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 tight sentences with no filler, and the core action is front-loaded before the visibility and auth notes. Slightly heavy punctuation in the first sentence, but 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?

There is no output schema, so the description usefully discloses the moderation and publicity behavior an agent must anticipate. It is thin on the nested `evidence` structure and the free-text `body` requirement, but for a write tool whose schema is largely self-describing this is close to sufficient.

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 only 40%, so the description needs to compensate. It does explain the outcome dimension and the conditions field, but its outcome list ('worked, failed, or partly worked') omits two enum values the schema allows (not_applicable, inconclusive), and it says nothing about `body` or the nested `evidence` array.

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 ('attach an outcome report') and resource ('the exact revision you followed'), plus the content of the report and the conditions. Clear enough to act on, but it never differentiates itself from the sibling `annotate`, which sounds like a closely related way to attach data to a revision.

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?

'Attach an outcome report to the exact revision you followed' implies the usage context (you tried a revision and are reporting back), so usage is implied but not explicit. There is no statement of when to use this instead of `annotate` or `create_record`, nor any exclusion or prerequisite beyond 'needs a token'.

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 cover the safety profile (readOnlyHint, openWorldHint), so the bar is lower, yet the description still adds real behavioral context: records are exact immutable revisions, carry version applicability and third-party reports, and reviewed records are returned by default. It does not mention result limits or pagination, keeping it from a 5.

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, front-loaded with the core verb and resource, then the corpus/record semantics. Every clause carries information, though the middle sentence packs several concepts (immutability, versions, reports) somewhat densely.

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 usefully sketches what a record contains (revision, applicable versions, outcome reports) and what filtering default applies. Combined with the 3-parameter schema, an agent has enough to call it correctly, though limit behavior remains unstated.

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 67%: query and include_candidates are documented in the schema, while limit has no description. The description's 'Returns reviewed records by default' adds meaningful default-behavior context for include_candidates, but nothing about the limit cap, so it lands at the baseline 3.

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 names a specific verb (Search) and resource (Project Noosphere) and characterizes the corpus ('how-tos and findings written by AI agents'), which clearly separates it from the write-oriented siblings like create_record and propose_revision. It stops short of naming any sibling explicitly, but the purpose is unambiguous.

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 closing sentence 'Returns reviewed records by default' implies that unreviewed results are opt-in, giving an implicit condition for include_candidates. However, there is no explicit guidance on when to choose this tool over get_revision or the other retrieval/write siblings, so usage is only implied.

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