996.fm perspective graph

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

Annotations already cover the safety profile (readOnly, non-destructive), and the description adds substantial behavior: results are a bounded sample (up to 4 debates, 36 stances), the graph does not encode opposition so the agent must infer it, hedged claims must stay hedged, and each stance carries speaker, date, strength, scope qualifiers and a receipt. This is rich disclosure well beyond the annotations.

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 purpose is front-loaded in the first sentence and the size suits a tool with this much behavioral nuance. A few procedural sentences (formatting the receipt, altitude matching) are dense but each carries usable instruction, so little 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?

With no output schema, the description carries the return-shape burden and does so thoroughly: result counts, per-stance fields, receipt format, sampling caveat, and the follow-up call. An agent has everything needed to call and interpret the results.

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?

With a single parameter and 100% schema coverage, the schema already documents 'topic'. The description adds only marginal interpretive value ('respect the question's altitude'), so the baseline 3 is appropriate.

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 opening sentence states a specific verb and resource ('Route a founder's dilemma to the debates that genuinely bear on it'), so the agent knows this maps a question to matching debates. It distinguishes from get_stances by naming that sibling as the way to get complete stances. It does not differentiate from list_debates or trace_evolution, so it falls short of full sibling-level clarity.

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?

It gives real routing criteria ('debates that genuinely bear on it'), states the fallback when coverage is thin ('advise from general knowledge rather than stretching a weak match'), and names get_stances as the alternative for full stances. It lacks explicit when-not-to-use guidance relative to list_debates or trace_evolution, but the context for use is clear.

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?

With annotations covering safety (readOnly, idempotent, non-destructive, closed-world), the description adds real behavioral context: the ±90s window, that written claims return only the snapshotted excerpt and 'never the surrounding text, never a live fetch' (a staleness caveat). This is meaningful disclosure beyond the annotations without contradicting them.

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 scoping statement is front-loaded, and the two retrieval modes are subdivided cleanly. The phrasing is somewhat flourishy ('The scene around one claim') but every clause carries content, and the receipt guidance 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 carries the return-value burden well, explaining exactly what comes back for spoken vs written claims. For a one-parameter, read-only tool the only remaining gap is the claim_id format, which is minor at this 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?

The single parameter claim_id has 0% schema description coverage, so the schema contributes nothing. The description implies a claim carries a timestamp and source (episode or essay), giving context for what claim_id references, but it never specifies the identifier's format or how to obtain it, so it only partially compensates.

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 resource and scope: it returns the episode transcript windowed ±90s around a claim, or the verbatim essay excerpt plus a link. It distinguishes the two retrieval modes (spoken vs written) clearly. It does not explicitly name or contrast the siblings (find_perspectives, get_stances, etc.), but the returned artifact 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?

Usage is implied rather than stated: 'so the founder can check the moment' signals this is a verification/receipt tool. However, there is no explicit when-to-use condition relative to the four sibling tools, and no when-not guidance, leaving the agent to infer selection.

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 (readOnly, idempotent, closed-world, non-destructive), so the bar is lower; the description still adds real behavioral context by stating the result is grouped by reading, contains no synthesis, is attributed and dated, and that dates are episode publication dates. It doesn't cover ordering or volume of results, but that is a minor gap given the annotation coverage.

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, front-loaded with what is returned before the caveat about synthesis. Some phrasing ('who-would-push-back read') is idiosyncratic, but nothing is redundant.

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 has to describe the return shape, and it does: stances grouped by reading, individually attributed and dated, unsynthesized. That is enough for an agent to use the result correctly; only the debate_id parameter and pagination/ordering remain unaddressed.

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 debate_id, so the schema contributes nothing. The description only indirectly signals the parameter's meaning ('one debate'), without explaining the identifier's format or source; a modest 3 for implying scoping but not documenting the parameter.

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+resource ('every stance on one debate') and a scoping behavior ('grouped by reading'), which is far more precise than the title alone. It does not name or contrast itself against any sibling (find_perspectives, get_context, trace_evolution), so an agent still has to infer which retrieval tool fits which need.

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?

'No synthesis' and 'raw material for your own who-would-push-back read' imply you use this when you want unprocessed positions rather than an aggregated answer, which is useful implied guidance. However, no alternative is named and no explicit when-to-use/when-not condition is given, leaving the choice among the four siblings 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, and closed-world, so safety is settled. The description adds genuinely new behavioral context beyond annotations: the default min-stance filter (2+), the 120-row page size, and how the tail line signals the next offset for paging.

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?

Compact and front-loaded: returned fields first, then filtering, then the routing constraint, then pagination defaults. No redundant or filler clauses; each sentence carries distinct 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 no output schema, the description compensates by listing the result columns, and it covers filtering, default thresholds, and offset-based pagination end to end. An agent has everything needed to call and page it correctly.

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 four parameters are already documented with types, bounds, and defaults. The description largely restates that (substring filter, 120 rows, 2+ stances default) without adding new syntax or edge-case meaning, which is the expected baseline when the schema does the heavy lifting.

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?

Names a specific verb and resource ('Browse the debate registry') and enumerates the returned fields (id, question, readings, stance count, born). It explicitly distinguishes itself from the sibling find_perspectives, so an agent can route correctly without opening either 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?

States the use case ('Browsing only — it does not rank against a question') and names the alternative for the other case ('use find_perspectives for that'). The when-to-use / when-not-to-use / alternative triad is fully covered.

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 (readOnly, idempotent, closed-world, non-destructive), and the description adds real behavioral context beyond them: results are ordered by publication date, every position must be dated and attributed, hedged claims stay hedged, and both sides of a reversal are surfaced. This is meaningful output-shaping guidance, though it omits any note on result size or pagination.

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 purpose and its distinguishing ordering are front-loaded, and the piece is short. The final sentence ('A 2023 position is a 2023 position') restates the earlier 'never judged' intent, costing a little density.

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, no-output-schema read tool, the description supplies what the agent needs: the record set, its ordering, the optional debate scope, and the attribution/hedging expectations. Nothing essential is missing, though a note on result volume would round it out.

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 0%, so the description must carry the parameters, and it does map both: 'one speaker' identifies the required person and 'optionally on one debate' clarifies that debate_id is an optional scope filter. It still omits format expectations (e.g., name form or debate_id style), so the compensation is partial.

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 and resource: one speaker's takes ordered by episode publication date, optionally scoped to one debate. The 'in order of publication date' framing clearly separates it from a static stance lookup, but the siblings (find_perspectives, get_stances) are never named, so differentiation is left 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 implied well enough ('one speaker's takes... optionally on one debate') to signal when the tool fits and what the debate_id scoping does. However, there is no explicit when-to-use versus find_perspectives/get_stances guidance and no exclusions, so the agent must infer the choice from sibling names.

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